WO2022004495A1 - 障害物検出装置及び障害物検出方法 - Google Patents
障害物検出装置及び障害物検出方法 Download PDFInfo
- Publication number
- WO2022004495A1 WO2022004495A1 PCT/JP2021/023647 JP2021023647W WO2022004495A1 WO 2022004495 A1 WO2022004495 A1 WO 2022004495A1 JP 2021023647 W JP2021023647 W JP 2021023647W WO 2022004495 A1 WO2022004495 A1 WO 2022004495A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- obstacle
- detection
- region
- coordinate
- detection device
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 286
- 238000009795 derivation Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 description 31
- 239000013256 coordination polymer Substances 0.000 description 12
- 238000012545 processing Methods 0.000 description 10
- 238000009434 installation Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001678 irradiating effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
- B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
- B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
- B66F9/075—Constructional features or details
- B66F9/0755—Position control; Position detectors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
- B66F17/00—Safety devices, e.g. for limiting or indicating lifting force
- B66F17/003—Safety devices, e.g. for limiting or indicating lifting force for fork-lift trucks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66F—HOISTING, LIFTING, HAULING OR PUSHING, NOT OTHERWISE PROVIDED FOR, e.g. DEVICES WHICH APPLY A LIFTING OR PUSHING FORCE DIRECTLY TO THE SURFACE OF A LOAD
- B66F9/00—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes
- B66F9/06—Devices for lifting or lowering bulky or heavy goods for loading or unloading purposes movable, with their loads, on wheels or the like, e.g. fork-lift trucks
- B66F9/075—Constructional features or details
- B66F9/20—Means for actuating or controlling masts, platforms, or forks
- B66F9/24—Electrical devices or systems
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30261—Obstacle
Definitions
- This disclosure relates to an obstacle detection device and an obstacle detection method.
- a moving object such as a vehicle is equipped with an obstacle detection device for detecting obstacles.
- the obstacle detection device disclosed in Patent Document 1 includes a sensor for detecting an obstacle and a position detecting unit for detecting the position of the obstacle from the detection result of the sensor.
- the position detection unit detects the position of an obstacle existing in the detectable area of the sensor.
- a stereo camera is used as the sensor.
- the position detection unit derives a parallax image from the image captured by the stereo camera, and detects the position of the obstacle based on the parallax image.
- An object of the present disclosure is to provide an obstacle detection device and an obstacle detection method capable of suppressing the detection of a part of a moving object as an obstacle.
- the obstacle detection device that solves the above problems is an obstacle detection device mounted on a moving body, and is a sensor for detecting an obstacle and a position for detecting the position of the obstacle from the detection result of the sensor.
- a detection unit is provided, and the position detection unit includes a region preset in a detectable region in which the obstacle can be detected by the sensor, and a region in which a part of the moving body is present is defined as a non-detection region. Then, in the non-detection region, there are a non-detection unit that determines that the obstacle does not exist regardless of the detection result of the sensor, and a detection region that is a region different from the non-detection region in the detectable region.
- a detection unit for detecting the position of the obstacle is provided.
- a non-detectable area is set in advance in the detectable area.
- the non-detection unit determines that there is no obstacle in the non-detection area even if an obstacle exists in the non-detection area. Since a part of the moving body exists in the non-detection area, by determining that there is no obstacle in the non-detection area, the obstacle detection device detects a part of the moving body as an obstacle. Can be suppressed.
- the moving body may be a forklift, and the non-detection region may be set at a position where a counterweight of the forklift exists.
- the position detection unit uses the X-axis as one axis in the horizontal direction, the Y-axis as the axis in the direction orthogonal to the X-axis in the horizontal direction, and the X-axis and the Y-axis.
- a coordinate derivation unit for deriving the coordinates of the obstacle in a coordinate system in real space whose axis in the orthogonal direction is the Z axis may be provided.
- the non-detection region may be defined by three-dimensional coordinates indicating a region in which a part of the moving body exists in the coordinate system in the real space.
- the obstacle detection method that solves the above-mentioned problems is an obstacle detection method that is mounted on a moving body and detects the position of an obstacle by an obstacle detection device including a sensor and a position detection unit.
- the position detection unit does not include the step of acquiring the detection result of the sensor and the region preset in the detectable region where the obstacle can be detected by the sensor and in which a part of the moving body is present.
- the position detection unit determines that the obstacle does not exist in the non-detection area regardless of the detection result of the sensor, and the position detection unit determines that the obstacle is not present in the non-detection area. It may include a step of detecting the position of the obstacle existing in the detection area which is a region different from the non-detection area.
- the side view of the forklift in the 1st Embodiment The plan view of the forklift in the first embodiment.
- the schematic block diagram of the forklift and the obstacle detection apparatus in 1st Embodiment The figure which shows an example of the 1st image taken by a stereo camera.
- a flowchart showing an obstacle detection process performed by the position detection device The figure for demonstrating the detectable area, the non-detection area, and the detection area.
- the schematic diagram which shows the position of the obstacle in the XY plane of the world coordinate system.
- the side view of the forklift in the 2nd Embodiment The figure which shows an example of the 1st image taken by a stereo camera.
- the forklift 10 as a moving body includes a vehicle body 11, a drive wheel 12 arranged at the front lower portion of the vehicle body 11, and a steering wheel 13 arranged at the rear lower portion of the vehicle body 11.
- a cargo handling device 17 is provided.
- the vehicle body 11 includes a head guard 14 provided on the upper part of the driver's seat, and a counterweight 15 for balancing the load loaded on the cargo handling device 17.
- the counterweight 15 is provided at the rear of the vehicle body 11.
- the forklift 10 may be operated by the operation by the passenger, may be automatically operated, or may be switched between manual operation and automatic operation.
- the left and right are the left and right when the forward direction of the forklift 10 is used as a reference.
- the forklift 10 includes a main control device 20, a traveling motor M1, a traveling control device 23 for controlling the traveling motor M1, and a rotation speed sensor 24.
- the main control device 20 controls the traveling operation and the cargo handling operation.
- the main control device 20 includes a processor 21 and a storage unit 22.
- the storage unit 22 includes RAM: RandomAccessMemory and ROM: ReadOnlyMemory.
- the storage unit 22 stores a program for operating the forklift 10. It can be said that the storage unit 22 stores a program code or a command configured to cause the processor 21 to execute the process.
- the main control device 20 may be configured by a hardware circuit such as ASIC: Application Specific Integrated Circuit or FPGA: Field Programmable Gate Array.
- the main control unit 20, which is a processing circuit, may include one or more processors operating according to a computer program, one or more hardware circuits such as ASICs and FPGAs, or a combination thereof.
- the main control device 20 gives a command of the rotation speed of the traveling motor M1 to the traveling control device 23 so that the vehicle speed of the forklift 10 becomes the target vehicle speed.
- the travel control device 23 of this embodiment is a motor driver.
- the rotation speed sensor 24 outputs the rotation speed of the traveling motor M1 to the traveling control device 23.
- the travel control device 23 controls the travel motor M1 so that the rotation speed of the travel motor M1 matches the command based on the command from the main control device 20.
- the forklift 10 is equipped with an obstacle detection device 30.
- the obstacle detection device 30 includes a stereo camera 31 as a sensor and a position detection device 41 that detects the position of an obstacle from an image captured by the stereo camera 31.
- the stereo camera 31 is installed so that the road surface on which the forklift 10 travels can be seen from above the forklift 10.
- the stereo camera 31 of the present embodiment images the rear of the forklift 10. Therefore, the obstacle detected by the position detection device 41 becomes an obstacle behind the forklift 10.
- the stereo camera 31 is installed in, for example, the head guard 14. As shown in FIG. 2, the stereo camera 31 is installed so as to deviate from the center position CP in the vehicle width direction of the forklift 10. In the present embodiment, the stereo camera 31 is installed so as to be offset to the left from the center position CP in the vehicle width direction of the forklift 10.
- the stereo camera 31 captures an imaging range determined by a horizontal angle of view and a vertical angle of view.
- the counterweight 15 is included in the range of the vertical angle of view. Therefore, a part of the counterweight 15 which is a part of the forklift 10 is always included in the image captured by the stereo camera 31.
- the stereo camera 31 includes a first camera 32 and a second camera 33.
- the first camera 32 and the second camera 33 include those using a CCD image sensor and a CMOS image sensor.
- the first camera 32 and the second camera 33 are arranged so that their optical axes are parallel to each other.
- the first camera 32 and the second camera 33 are arranged side by side in the horizontal direction with each other. Assuming that the image captured by the first camera 32 is the first image and the image captured by the second camera 33 is the second image, the same obstacle appears laterally shifted in the first image and the second image. Become.
- the obstacle shown in the first image and the obstacle shown in the second image have the first camera 32 and the second camera 33 in the horizontal pixel [px]. There will be a gap depending on the distance between them.
- the first image and the second image are, for example, images represented by RGB signals.
- the position detection device 41 includes a processor 42 and a storage unit 43.
- the processor 42 for example, a CPU, a GPU, and a DSP are used.
- the storage unit 43 includes RAM and ROM.
- the storage unit 43 stores various programs for detecting obstacles from the image captured by the stereo camera 31. It can be said that the storage unit 43 stores a program code or a command configured to cause the processor 42 to execute the process.
- the storage 43 i.e., a computer-readable medium, includes any available medium accessible by a general purpose or dedicated computer.
- the position detection device 41 may be configured by a hardware circuit such as an ASIC or FPGA.
- the position detection device 41 which is a processing circuit, may include one or more processors operating according to a computer program, one or more hardware circuits such as ASICs and FPGAs, or a combination thereof.
- the obstacle detection process is performed by the processor 42 executing the program stored in the storage unit 43.
- the obstacle detection process is repeated in a predetermined control cycle.
- FIG. 4 is a first image I1 obtained by imaging the rear of the forklift 10. As can be seen from the first image I1, there are people and obstacles other than people behind the forklift 10. A part of the counterweight 15 is reflected in the first image I1.
- the coordinates on the first image I1 in which the obstacle exists are shown by the frames A1, A2, A3, A4, but in the actual first image I1, the frames A1, A2, A3, A4 are shown. not exist.
- step S1 the position detection device 41 acquires the first image I1 and the second image of the same frame from the image captured by the stereo camera 31.
- the first image I1 and the second image are the detection results of the stereo camera 31.
- the position detection device 41 acquires a parallax image by performing stereo processing.
- the parallax image is an image in which the parallax [px] is associated with the pixels.
- the parallax is obtained by comparing the first image I1 and the second image and calculating the difference in the number of pixels between the first image I1 and the second image for the same feature point appearing in each image.
- the feature point is a part that can be recognized as a boundary, such as the edge of an obstacle.
- the feature points can be detected from the luminance information and the like.
- the position detection device 41 converts RGB to YCrCb using a RAM that temporarily stores each image.
- the position detection device 41 may perform distortion correction, edge enhancement processing, and the like.
- the position detection device 41 performs stereo processing for calculating the parallax by comparing the similarity between each pixel of the first image I1 and each pixel of the second image.
- stereo processing a method of calculating the parallax for each pixel may be used, or a block matching method of dividing each image into blocks containing a plurality of pixels and calculating the parallax for each block may be used. ..
- the position detection device 41 acquires a parallax image using the first image I1 as a reference image and the second image as a comparison image.
- the position detection device 41 extracts the pixels of the second image most similar to each pixel of the first image I1, and the difference between the pixels of the first image I1 and the number of pixels in the horizontal direction most similar to the pixels. Is calculated as the parallax. As a result, it is possible to acquire a parallax image in which parallax is associated with each pixel of the first image I1 which is a reference image.
- the parallax image does not necessarily require display, and indicates data in which parallax is associated with each pixel in the parallax image.
- the position detection device 41 may perform a process of removing the parallax on the road surface from the parallax image.
- the position detection device 41 derives the coordinates of the feature points in the world coordinate system.
- the camera coordinate system is a coordinate system with the stereo camera 31 as the origin.
- the camera coordinate system is a three-axis Cartesian coordinate system in which the optical axis is the Z axis and the two axes orthogonal to the optical axis are the X axis and the Y axis, respectively.
- the coordinates of the feature points in the camera coordinate system can be represented by Z coordinate Zc, X coordinate Xc, and Y coordinate Yc in the camera coordinate system.
- the Z coordinate Zc, the X coordinate Xc, and the Y coordinate Yc can be derived using the following equations (1) to (3), respectively.
- B is the baseline length [mm]
- f is the focal length [mm]
- d is the parallax [px].
- xp is an arbitrary X coordinate in the parallax image, and x'is the X coordinate of the center coordinate of the parallax image.
- yp is an arbitrary Y coordinate in the parallax image, and y'is the Y coordinate of the center coordinate of the parallax image.
- the feature point in the camera coordinate system can be used.
- the coordinates are derived.
- the axis extending in the vehicle width direction of the forklift 10 in the horizontal direction is the X axis
- the axis extending in the direction orthogonal to the X axis in the horizontal direction is the Y axis, X.
- a 3-axis Cartesian coordinate system whose Z axis is an axis orthogonal to the axis and the Y axis is a world coordinate system which is a coordinate system in real space.
- the Y axis of the world coordinate system can be said to be an axis extending in the front-rear direction of the forklift 10, which is the traveling direction of the forklift 10.
- the Z axis of the world coordinate system can be said to be an axis extending in the vertical direction.
- the coordinates of the feature points in the world coordinate system can be represented by the X coordinate Xw, the Y coordinate Yw, and the Z coordinate Zw in the world coordinate system.
- the position detection device 41 performs world coordinate conversion that converts camera coordinates to world coordinates using the following equation (4).
- World coordinates are coordinates in the world coordinate system.
- H in the equation (4) is the installation height [mm] of the stereo camera 31 in the world coordinate system
- ⁇ is the angle + 90 ° between the optical axes of the first camera 32 and the second camera 33 and the horizontal plane. The angle of.
- the origin of the world coordinate system is the coordinates where the X coordinate Xw and the Y coordinate Yw are the positions of the stereo camera 31 and the Z coordinate Zw is the road surface.
- the position of the stereo camera 31 is, for example, an intermediate position between the lens of the first camera 32 and the lens of the second camera 33.
- the X coordinate Xw indicates the distance from the origin to the feature point in the vehicle width direction of the forklift 10.
- the Y coordinate Yw indicates the distance from the origin to the feature point with respect to the traveling direction of the forklift 10.
- the Z coordinate Zw indicates the height from the road surface to the feature point. Characteristic points are points that represent a part of an obstacle.
- the arrow X indicates the X axis of the world coordinate system
- the arrow Y indicates the Y axis of the world coordinate system
- the arrow Z indicates the Z axis of the world coordinate system.
- the area where the world coordinates can be acquired is the detectable area CA, which is the area where obstacles can be detected.
- the detectable region CA is determined by, for example, the imaging range of the stereo camera 31.
- the non-detection area NA1 is set in advance in the detectable area CA of the stereo camera 31.
- the non-detection region NA1 is a region where it is determined that there is no obstacle regardless of whether or not the obstacle is imaged by the stereo camera 31.
- the region of the detectable region CA that is different from the non-detectable region NA1 is designated as the detection region DA.
- the detection area DA is an area where obstacles are detected. Therefore, it can be said that the position detection device 41 detects an obstacle when the obstacle is imaged by the stereo camera 31 and the obstacle is present in the detection area DA.
- step S4 the position detection device 41 deletes the feature points in the non-detection region NA1 as unnecessary feature points.
- the non-detection region NA1 is set at a position in the detectable region CA where a part of the forklift 10 exists.
- the position where the counterweight 15 exists is the non-detection region NA1. It can be said that the unnecessary feature points are the feature points generated by the image of the counterweight 15.
- Unnecessary feature points can be derived from the vehicle specifications.
- the vehicle specifications for deriving unnecessary feature points are stored in, for example, the storage unit 43 of the position detection device 41.
- Information indicating each of the distance W2 in the vehicle width direction between the stereo camera and the stereo camera 31 is stored as vehicle specifications.
- the width W1 of the counterweight 15 is the dimension of the counterweight 15 in the vehicle width direction.
- the width W1 of the counterweight 15 can be said to be the dimension of the counterweight 15 in the X-axis direction in the world coordinate system.
- the counterweight 15 imaged by the stereo camera 31 has a constant width. Therefore, the width W1 of the counterweight 15 can be set to a constant value.
- the width W1 of the counterweight 15 may be stored according to the position of the counterweight 15 in the front-rear direction.
- the width of the counterweight 15 may be grasped even when the width of the counterweight 15 is not constant. ..
- the width of the counterweight 15 may be regarded as constant.
- the maximum width of the counterweight 15 may be regarded as the width of the counterweight 15.
- the height H1 of the counterweight 15 is the dimension from the road surface to the upper end of the counterweight 15. Since the origin of the Z axis in the world coordinate system is the road surface, the height H1 of the counterweight 15 can be said to be the Z coordinate Zw at the upper end of the counterweight 15 in the world coordinate system. When the height of the counterweight 15 differs depending on the position in the front-rear direction or the position in the vehicle width direction of the counterweight 15, the highest position may be the upper end of the counterweight 15.
- the distance L1 in the front-rear direction from the stereo camera 31 to the rear end of the counter weight 15 is a dimension in the Y-axis direction from the stereo camera 31 to the rear end of the counter weight 15 in the world coordinate system. Since the origin of the Y axis in the world coordinate system is the stereo camera 31, the distance L1 in the front-rear direction from the stereo camera 31 to the rear end of the counter weight 15 is also the Y coordinate Yw of the rear end of the counter weight 15 in the world coordinate system. I can say. If the position of the rear end of the counterweight 15 differs depending on the position in the front-rear direction or the position in the vehicle width direction of the counterweight 15, the rearmost position may be the rear end of the counterweight 15.
- the distance W2 between the center position CP of the forklift 10 and the stereo camera 31 in the vehicle width direction is the dimension in the X-axis direction from the center position CP of the forklift 10 to the stereo camera 31 in the world coordinate system. Since the origin of the X axis in the world coordinate system is the stereo camera 31, the distance W2 between the center position CP of the forklift 10 and the stereo camera 31 in the vehicle width direction is the X coordinate Xw of the center position CP of the forklift 10 in the world coordinate system. It can be said that.
- the position detection device 41 deletes feature points that meet all of the following first condition, second condition, and third condition from the above-mentioned vehicle specifications as unnecessary feature points.
- First condition ...- (W1 / 2 + W2) ⁇ Xw ⁇ (W1 / 2-W2)
- Second condition ... 0 ⁇ Yw ⁇ L1
- Third condition ... 0 ⁇ Zw ⁇ H1
- the first condition is to extract feature points in the range of half the width W1 of the counterweight 15 for each of both sides in the X-axis direction of the world coordinate system from the center position CP in the vehicle width direction of the forklift 10. It can be said that.
- the range of the X coordinate Xw is forked lifted by shifting the X coordinate Xw to the right by the distance W2. It can be said that the distance is offset to the range based on the center position CP of 10.
- the second condition is to extract the feature points existing in the range from the stereo camera 31 to the rear end of the counterweight 15.
- the third condition is that the feature points from the road surface to the upper end of the counterweight 15 are extracted.
- each condition indicates the range of three-dimensional coordinates in the world coordinate system.
- a rectangular parallelepiped region in which the range of the X coordinate Xw is-(W1 / 2 + W2) to (W1 / 2-W2), the range of the Y coordinate Yw is 0 to L1, and the range of the Z coordinate Zw is 0 to H1 is a feature point.
- the non-detection region NA1 can be said to be a region surrounded by coordinates P1 to P8 in the world coordinate system.
- the coordinates P1 are (-(W1 / 2 + W2), 0, H1)
- the coordinates P2 are (W1 / 2-W2,0, H1).
- the coordinate P3 can be represented by ( ⁇ (W1 / 2 + W2), L1, H1)
- the coordinate P4 can be represented by (W1 / 2-W2, L1, H1).
- the coordinate P5 is (-(W1 / 2 + W2), 0,0)
- the coordinate P6 is (W1 / 2-W2,0,0)
- the coordinate P7 is (-(W1 / 2 + W2), L1,0).
- the coordinates P8 can be represented by (W1 / 2-W2, L1,0).
- the non-detection region NA1 is defined by three-dimensional coordinates indicating an region in which the counterweight 15 exists in the world coordinate system.
- the + coordinate or-coordinate in the world coordinates indicates in which direction the coordinates are located with respect to the origin of the world coordinate system, and can be arbitrarily set for each coordinate axis.
- the X coordinate Xw has a + coordinate to the left of the origin and a-coordinate to the right of the origin.
- the Y coordinate Yw has a + coordinate behind the origin and a-coordinate ahead of the origin.
- the Z coordinate Zw has a + coordinate above the origin and a-coordinate below the origin.
- the position detection device 41 extracts an obstacle existing in the world coordinate system.
- the position detection device 41 sets a set of feature points that are assumed to represent the same obstacle out of a plurality of feature points that represent a part of the obstacle as one point cloud, and extracts the point cloud as an obstacle. ..
- the position detection device 41 performs clustering in which the feature points located within a predetermined range are regarded as one point cloud from the world coordinates of the feature points derived in step S3.
- the position detection device 41 regards the clustered point cloud as one obstacle.
- the obstacle extracted in step S5 can be said to be an obstacle existing in the detection region DA, which is a region different from the non-detection region NA1.
- the feature point clustering performed in step S5 can be performed by various methods. That is, the clustering may be performed by any method as long as it can be regarded as an obstacle by forming a plurality of feature points into one point cloud.
- the position detection device 41 derives the position of the obstacle extracted in step S5.
- the position of the obstacle is the coordinates of the obstacle in the XY plane of the world coordinate system.
- the position detection device 41 can recognize the world coordinates of an obstacle from the world coordinates of the feature points constituting the clustered point cloud.
- the X-coordinate Xw, Y-coordinate Yw, and Z-coordinate Zw of a plurality of feature points located at the ends of the clustered point group may be the X-coordinate Xw, Y-coordinate Yw, and Z-coordinate Zw of the obstacle.
- the X-coordinate Xw, Y-coordinate Yw, and Z-coordinate Zw of the feature point that is the center of the point group may be the X-coordinate Xw, Y-coordinate Yw, and Z-coordinate Zw of the obstacle. That is, the coordinates of the obstacle in the world coordinate system may represent the entire obstacle or may represent one point of the obstacle.
- the position detection device 41 projects the X-coordinate Xw, Y-coordinate Yw, and Z-coordinate Zw of the obstacle onto the XY plane of the world coordinate system, thereby projecting the obstacle on the XY plane of the world coordinate system.
- Obstacles O1 to O4 shown in FIG. 7 are obstacles detected from the first image I1 and the second image by performing the processes of steps S1 to S6.
- the obstacle O1 is an obstacle existing in the frame A1.
- the obstacle O2 is an obstacle existing in the frame A2.
- the obstacle O3 is an obstacle existing in the frame A3.
- the obstacle O4 is an obstacle existing in the frame A4.
- the position detection device 41 extracts the obstacle O5 corresponding to the counterweight 15.
- the feature points of the non-detection region NA1 are deleted, and it is determined that no obstacle exists in the non-detection region NA1 to suppress the extraction of the obstacle O5.
- the position detection device 41 functions as a non-detection unit.
- the position detection device 41 functions as a detection unit.
- the position detection device 41 functions as a position detection unit.
- step S4 means that the feature points in the non-detection region NA1 are not used for the extraction of obstacles in step S5. That is, “deletion of feature points” is not only an embodiment in which the world coordinates of feature points in the non-detection area NA1 are deleted from the RAM of the position detection device 41, but also feature points in the non-detection area NA1 from the RAM of the position detection device 41. It includes an embodiment in which the feature points of the non-detection region NA1 are not used for the extraction of obstacles without deleting the world coordinates of.
- the main control device 20 grasps the positional relationship between the forklift 10 and the obstacle in the horizontal direction by acquiring the detection result by the position detection device 41.
- the main control device 20 controls according to the positional relationship between the forklift 10 and an obstacle. For example, the main control device 20 limits the vehicle speed or gives an alarm when the distance between the forklift 10 and an obstacle falls below the threshold value.
- the non-detectable area NA1 is set in advance in the detectable area CA.
- the position detection device 41 deletes the feature points existing in the non-detection region NA1. As a result, the position detection device 41 determines that there is no obstacle in the non-detection region NA1 even if an obstacle exists in the non-detection region NA1.
- the non-detection region NA1 is an region in which the counterweight 15 exists. Since the positional relationship between the stereo camera 31 and the counterweight 15 is constant, the counterweight 15 always falls within the imaging range of the stereo camera 31.
- the counterweight 15 When the main control device 20 issues a vehicle speed limit or an alarm according to the distance to an obstacle, the counterweight 15 may be detected as an obstacle and the vehicle speed limit or an alarm may be issued. Since the counterweight 15 always enters the detectable region CA, there is a possibility that the vehicle speed limit or the alarm will always be given. In this case, the forklift 10 may deteriorate the work efficiency. Further, if an alarm is always issued, it may not be possible to determine whether or not the forklift 10 and an obstacle are close to each other.
- the counterweight 15 since the counterweight 15 is not detected as an obstacle, the counterweight 15 is imaged by the stereo camera 31 to suppress the vehicle speed limitation and the warning.
- the non-detection area NA1 is set in advance in the detectable area CA of the stereo camera 31.
- the position detection device 41 determines that there is no obstacle in the non-detection region NA1 by deleting the feature points in the non-detection region NA1. It is possible to prevent the counterweight 15 existing in the non-detection region NA1 from being detected as an obstacle.
- a counterweight 15 is arranged behind the vehicle body 11 in order to balance with the load loaded on the cargo handling device 17. Therefore, the counterweight 15 tends to enter the detectable region CA of the stereo camera 31 that captures the rear image. Further, it may be difficult to arrange the stereo camera 31 so that the counterweight 15 does not enter the detectable area CA due to the arrangement restriction.
- the area where the counterweight 15 exists as the non-detection area NA1 even if the counterweight 15 enters the detectable area CA of the stereo camera 31, the counterweight 15 is detected as an obstacle. Obstacles in the detection area DA can be detected while suppressing them.
- the non-detection area NA1 is defined by the three-dimensional coordinates of the world coordinate system. It is also possible to define the non-detection region NA1 by the X coordinate Xw and the Y coordinate Yw of the world coordinate system and delete the feature points regardless of the Z coordinate Zw. In this case, even if an obstacle is placed on the counterweight 15, this obstacle is also included in the non-detection region NA1. Therefore, even if an obstacle is present on the counterweight 15, it is considered that this obstacle does not exist. By defining the non-detection region NA1 with three-dimensional coordinates, it is possible to detect an obstacle existing on the counterweight 15.
- Non-detection area NA1 is a preset area.
- the position detecting device 41 is used. It is necessary to set the area where the movable member exists as the non-detection area. Since the movable member moves, the non-detection region cannot be set in advance, and the position detection device 41 needs to detect the position of the movable member and set this position as the non-detection region.
- the non-detection region NA1 is set corresponding to the counterweight 15 whose positional relationship with the stereo camera 31 is constant. Since the position of the counterweight 15 in the detectable area CA is constant, the non-detection area NA1 can be set in advance. Compared with the case where the position of the movable member is detected and the non-detection area is set according to this position, the load on the position detection device 41 can be reduced.
- the forklift 10 includes a mirror 18 and a support portion 19 that supports the mirror 18.
- the support portion 19 extends toward the rear of the vehicle body 11.
- the mirror 18 and the support portion 19 are located within the range of the vertical angle of view of the stereo camera 31.
- the mirror 18 and the support 19 are part of the forklift 10.
- the mirror 18 and the support portion 19 are included in the first image I1 captured by the stereo camera 31.
- an obstacle detection process is performed so that the mirror 18 and the support portion 19 are not detected as obstacles.
- the storage unit 43 of the position detection device 41 stores the height H2 of the mirror 18 as vehicle specifications.
- the height H2 of the mirror 18 is a dimension from the road surface to the lower end of the mirror 18. Since the origin of the Z axis in the world coordinate system is the road surface, the height H2 of the mirror 18 can be said to be the Z coordinate Zw of the lower end of the mirror 18 in the world coordinate system.
- the support portion 19 is located above the lower end of the mirror 18 as a whole.
- the position detection device 41 can delete the feature points generated by the mirror 18 and the support portion 19 as unnecessary feature points in addition to the counterweight 15. Is.
- the position detection device 41 deletes feature points that meet all of the first condition, the second condition, and the third condition as unnecessary feature points.
- Zw ⁇ H2 is added as an or condition. Therefore, the feature points that match 0 ⁇ Zw ⁇ H1 among the first condition, the second condition, and the third condition, and the feature points that match Zw ⁇ H2 among the first condition, the second condition, and the third condition. Both are deleted as unnecessary feature points.
- the non-detection region NA2 defined by Zw ⁇ H2 has an X coordinate Xw range of ⁇ (W1 / 2 + W2) to (W1 / 2-W2) and a Y coordinate Yw. It can be said that the range of is 0 to L1 and the Z coordinate Zw is H2 or more.
- the mirror 18 and the support portion 19 are no longer judged to be obstacles. Since the first condition and the second condition are the same as those in the first embodiment, the feature points in the same range as the counterweight 15 are deleted for the X coordinate Xw and the Y coordinate Yw. Depending on the size of the mirror 18 and the support portion 19, the range of the X coordinate Xw and the range of the Y coordinate Yw of the non-detection region NA2 may be excessive or insufficient with respect to the mirror 18 and the support portion 19. In this case, each condition may be set individually in the non-detection region NA1 for the counterweight 15 and the non-detection region NA2 for the mirror 18 and the support portion 19.
- the mirror 18 and the support portion 19 are suppressed from being detected as obstacles. Even when a plurality of members are in the detectable region CA, by setting the non-detection regions NA1 and NA2 for the plurality of members, each of the plurality of members can be detected without being regarded as an obstacle. Obstacles in region DA can be detected.
- the non-detection region NA1 may be defined by two-dimensional coordinates indicating the coordinates on the XY plane of the world coordinate system. That is, the third condition in each embodiment may be deleted, and the feature points satisfying the first condition and the second condition may be deleted. In this case, regardless of the Z coordinate Zw, the feature points existing in the non-detection region defined by the X coordinate Xw and the Y coordinate Yw are deleted as unnecessary feature points.
- the position of the obstacle derived in step S6 may be three-dimensional coordinates in the world coordinate system. It can be said that the position detection device 41 does not have to project the obstacle onto the XY plane of the world coordinate system.
- the obstacle detection device 30 may be a sensor capable of acquiring three-dimensional coordinates in the world coordinate system other than the stereo camera 31.
- this type of sensor include LIDAR: Laser Imaging Detection and Ringing, millimeter-wave radar, and TOF: Time of Flight cameras.
- LIDAR is a rangefinder that can recognize the surrounding environment by irradiating a laser while changing the irradiation angle and receiving the reflected light reflected from the part hit by the laser.
- the millimeter wave radar is capable of recognizing the surrounding environment by irradiating the surroundings with radio waves in a predetermined frequency band.
- the TOF camera includes a camera and a light source that irradiates light, and derives the distance in the depth direction for each pixel of the image captured by the camera from the time until the reflected light of the light emitted from the light source is received. It is a thing.
- the sensor may be a combination of the above-mentioned sensors.
- the obstacle detection device 30 may include, as a sensor, a two-dimensional LIDAR that irradiates a laser while changing the irradiation angle in the horizontal direction.
- LIDAR irradiates the laser while changing the irradiation angle within the range of the irradiation angle.
- the irradiation possible angle is, for example, 270 degrees with respect to the horizontal direction.
- the two-dimensional LIDAR detectable region CA is a range defined by the irradiation angle and the measurable distance. Assuming that the portion hit by the laser is the irradiation point, the two-dimensional LIDAR can measure the distance to the irradiation point in association with the irradiation angle.
- the two-dimensional LIDAR can measure the two-dimensional coordinates of the irradiation point when the two-dimensional LIDAR is the origin.
- the two-dimensional coordinates measured by the two-dimensional LIDAR are the coordinates of the world coordinate system in which one direction in the horizontal direction is the X axis and the direction orthogonal to the X axis in the horizontal direction is the Y axis.
- the non-detection area is defined by two-dimensional coordinates.
- the installation position of the stereo camera 31 may be changed as appropriate.
- the stereo camera 31 may be installed at the center position CP, for example.
- the first condition can be changed as follows.
- the non-detection region may be set to the image captured by the stereo camera 31.
- the coordinates of the first image I1 in which the counterweight 15 is captured can be grasped in advance from the installation position and the installation angle of the stereo camera 31.
- the coordinates in which the counterweight 15 is captured in the first image I1 are set as the non-detection region so that the parallax is not calculated in the non-detection region.
- the non-detection region may be set in at least one of the first image I1 and the second image. As for the position where the counterweight 15 appears, the feature points cannot be obtained, so that the same effect as that of each embodiment can be obtained.
- the coordinates reflected in the image can be set as the non-detection region.
- the detectable region CA is a range that enters the image captured by the stereo camera 31. More specifically, it is a range in which a parallax image can be acquired among the images captured by the stereo camera 31.
- the non-detection regions NA1 and NA2 need only include a region in which a part of the forklift 10 is present, and is a region larger than a region in which a part of the forklift 10 is present. May be good. That is, the non-detection regions NA1 and NA2 may be regions including a margin.
- the position detection device 41 may determine whether or not each obstacle exists in the non-detection region NA1 after the feature points are clustered in step S5 to extract obstacles.
- the position detection device 41 considers that the obstacle existing in the non-detection region NA1 does not exist.
- the position detection device 41 may consider that an obstacle straddling the inside and outside of the non-detection region NA1 exists in the non-detection region NA1, or may exist outside the non-detection region NA1. You may consider it to be.
- the position detection device 41 has an obstacle straddling the inside and outside of the non-detection region NA1, only the portion existing outside the non-detection region NA1 may be regarded as an obstacle.
- the whole of the detectable area CA other than the non-detection areas NA1 and NA2 may be used as the detection area DA, or a part of the detectable area CA other than the non-detection areas NA1 and NA2 may be used as the detection area DA. May be.
- the position detection device 41 may perform a process of determining whether the detected obstacle is a person or an object other than a person after performing the process of step S6. Whether or not an obstacle is a person can be determined by various methods. For example, the position detection device 41 determines whether or not an obstacle is a person by performing a person detection process on an image captured by any of the two cameras 32 and 33 of the stereo camera 31. .. The position detection device 41 converts the coordinates of the obstacle in the world coordinate system obtained in step S6 into the camera coordinates, and converts the camera coordinates into the coordinates of the images captured by the cameras 32 and 33. For example, the position detection device 41 converts the coordinates of an obstacle in the world coordinate system into the coordinates of the first image I1.
- the position detection device 41 performs a person detection process on the coordinates of the obstacle in the first image I1.
- the human detection process is performed using, for example, feature quantity extraction and a human determination device that has been machine-learned in advance.
- the feature amount extraction include a method of extracting the feature amount of a local region in an image such as HOG: Histogram of Oriented Gradients feature amount and Haar-Like feature amount.
- the human judgment device for example, a machine learning using a supervised learning model is used.
- a supervised learning model for example, a support vector machine, a neural network, naive bays, deep learning, a decision tree, or the like can be adopted.
- image-specific components such as human shape elements and appearance elements extracted from the image are used.
- the shape element include the size and contour of a person.
- the appearance element include light source information, texture information, camera information, and the like.
- the light source information includes information on reflectance, shading, and the like.
- the texture information includes color information and the like.
- the camera information includes information on image quality, resolution, angle of view, and the like.
- the time required for the person detection process is long, when detecting a person from the image, the coordinates where the obstacle exists are specified, and the person detection process is performed for those coordinates.
- the time required for the person detection process can be shortened as compared with the case where the person detection process is performed on the entire area of the image. Since a part of the forklift 10 such as the counterweight 15 is not determined to be an obstacle, the person detection process is not performed at the coordinates where the part of the forklift 10 is captured in the image. Therefore, the processing time can be shortened as compared with the case where a part of the forklift 10 is detected as an obstacle and the person detection processing is performed on the coordinates in which the obstacle is reflected.
- the entire counterweight 15 located behind the stereo camera 31 is set as the non-detection region NA1, but the non-detection region NA1 may be set in consideration of the range imaged by the stereo camera 31. good.
- the image of the stereo camera 31 is captured. There is a part that does not fit in the range. Therefore, the portion that does not enter the imaging range of the stereo camera 31 does not have to be included in the non-detection region NA1.
- the lower limit of the Y coordinate Yw of the second condition may be set to a value larger than 0.
- the coordinates defining the non-detection area may be stored in the storage unit 43 of the position detection device 41. If it is the non-detection region NA1, the coordinates P1 to P8 may be stored.
- the obstacle detection device 30 may detect an obstacle located in front of the forklift 10.
- the stereo camera 31 is installed so as to image the front of the forklift 10. Even when the stereo camera 31 images the front of the forklift 10, a part of the forklift 10 enters the detectable area CA of the stereo camera 31 depending on the installation position of the stereo camera 31.
- the non-detection region is set according to a part of the forklift 10 that enters the detectable region CA.
- the obstacle detection device 30 may detect obstacles on both sides in front of and behind the forklift 10.
- the stereo camera 31 is provided with both a camera that captures the front of the forklift 10 and a stereo camera 31 that captures the rear of the forklift 10.
- the world coordinate system is not limited to the orthogonal coordinate system and may be a polar coordinate system.
- the position detection unit may be composed of a plurality of devices.
- the position detection unit may individually include a device that functions as a non-detection unit, a device that functions as a detection unit, and a device that functions as a coordinate derivation unit.
- conversion from camera coordinates to world coordinates may be performed by table data.
- the table data is table data in which the combination of the Y coordinate Yc and the Z coordinate Zc corresponds to the Y coordinate Yw, and the table data in which the combination of the Y coordinate Yc and the Z coordinate Zc corresponds to the Z coordinate Zw.
- the first camera 32 and the second camera 33 may be arranged side by side in the vertical direction.
- the obstacle detection device 30 may include an auxiliary storage device configured to store various information such as information stored in the storage unit 43 of the position detection device 41.
- auxiliary storage device for example, a non-volatile storage device that can rewrite data such as a hard disk drive, a solid state drive, or an EEPROM: Electrically Erasable Programmable Read Only Memory is used.
- the stereo camera 31 may include three or more cameras. ⁇ In each embodiment, the stereo camera 31 may be attached to any position such as the cargo handling device 17.
- the forklift 10 may be driven by an engine.
- the travel control device is a device that controls the fuel injection amount to the engine and the like.
- the part of the forklift 10 may be other than the counterweight 15, the mirror 18, and the support portion 19, as long as it is a part of the forklift 10 and enters the detectable region CA. It may be something like.
- the obstacle detection device 30 can be mounted on various moving objects such as construction machines, automatic guided vehicles, industrial vehicles other than forklifts 10 such as trucks, passenger cars, and flying objects.
- Non-detection area 10 ... Forklift as a moving object 15 ... Counterweight that is part of the forklift 18 ... Mirror that is part of the forklift 19 ... Part of the forklift Support unit 30 ... Obstacle detection device 31 ... Stereo camera as a sensor 41 ... Position detection unit, non-detection unit, detection unit and position detection device as coordinate derivation unit
Landscapes
- Engineering & Computer Science (AREA)
- Structural Engineering (AREA)
- Transportation (AREA)
- Physics & Mathematics (AREA)
- Geology (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Civil Engineering (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Human Computer Interaction (AREA)
- Forklifts And Lifting Vehicles (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Geophysics And Detection Of Objects (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
Description
本開示の目的は、移動体の一部が障害物として検出されることを抑制できる障害物検出装置及び障害物検出方法を提供することにある。
上記障害物検出装置について、前記位置検出部は、水平方向のうち一方向の軸をX軸、水平方向のうち前記X軸に直交する方向の軸をY軸、前記X軸及び前記Y軸に直交する方向の軸をZ軸とする実空間上の座標系での前記障害物の座標を導出する座標導出部を備えていてもよい。
上記課題を解決する障害物検出方法は、移動体に搭載されており、かつ、センサと位置検出部とを備える障害物検出装置によって障害物の位置を検出する障害物検出方法であって、前記位置検出部が、前記センサの検出結果を取得するステップと、前記センサによって前記障害物を検出可能な検出可能領域に予め設定された領域であって前記移動体の一部が存在する領域を非検出領域とすると、前記位置検出部が、前記非検出領域には前記センサの検出結果に関わらず前記障害物が存在しないと判断するステップと、前記位置検出部が、前記検出可能領域のうち前記非検出領域とは異なる領域である検出領域に存在する前記障害物の位置を検出するステップと、を含んでいてもよい。
以下、障害物検出装置及び障害物検出方法の第1実施形態について説明する。
図1及び図2に示すように、移動体としてのフォークリフト10は、車体11と、車体11の前下部に配置された駆動輪12と、車体11の後下部に配置された操舵輪13と、荷役装置17と、を備える。車体11は、運転席の上部に設けられたヘッドガード14と、荷役装置17に積載される荷と釣り合いを取るためのカウンタウェイト15と、を備える。カウンタウェイト15は、車体11の後部に設けられている。フォークリフト10は、搭乗者による操作によって動作するものであってもよいし、自動で動作するものであってもよいし、手動での動作と自動での動作を切り替えられるものであってもよい。以下の説明において、左右とは、フォークリフト10の前進方向を基準とした場合の左右である。
図1及び図2に示すように、カウンタウェイト15の幅W1、カウンタウェイト15の高さH1、ステレオカメラ31からカウンタウェイト15の後端までの前後方向の距離L1、及びフォークリフト10の中心位置CPとステレオカメラ31との車幅方向の距離W2のそれぞれを示す情報が車両諸元として記憶されている。
第1条件…-(W1/2+W2)≦Xw≦(W1/2-W2)
第2条件…0≦Yw≦L1
第3条件…0≦Zw≦H1
第1条件は、フォークリフト10の車幅方向の中心位置CPから、ワールド座標系のX軸方向の両側のそれぞれに対して、カウンタウェイト15の幅W1の半分の範囲の特徴点を抽出しているといえる。本実施形態では、フォークリフト10の中心位置CPとワールド座標系におけるX軸の原点とが距離W2ずれているため、距離W2だけX座標Xwを右方にずらすことで、X座標Xwの範囲をフォークリフト10の中心位置CPを基準とした範囲にオフセットしているともいえる。
第3条件は、路面からカウンタウェイト15の上端までの特徴点を抽出しているといえる。
検出可能領域CAには、予め非検出領域NA1が設定されている。位置検出装置41は、非検出領域NA1に存在する特徴点を削除している。これにより、位置検出装置41は、非検出領域NA1に障害物が存在している場合であっても、非検出領域NA1には障害物が存在していないと判断する。非検出領域NA1は、カウンタウェイト15が存在している領域である。ステレオカメラ31とカウンタウェイト15の位置関係は一定であるため、ステレオカメラ31の撮像範囲には必ずカウンタウェイト15が入り込む。
(1-1)ステレオカメラ31の検出可能領域CAには、予め非検出領域NA1が設定されている。位置検出装置41は、非検出領域NA1の特徴点を削除することで、非検出領域NA1には障害物が存在していないと判断する。非検出領域NA1に存在するカウンタウェイト15が障害物として検出されることを抑制することができる。
以下、第2実施形態の障害物検出装置及び障害物検出方法について説明する。以下の説明において、第1実施形態と同様な部分については説明を省略する。
第1実施形態の第3条件に加えて、Zw≧H2がor条件として加えられている。従って、第1条件、第2条件、及び第3条件のうち0≦Zw≦H1に合致する特徴点と、第1条件、第2条件及び第3条件のうちZw≧H2に合致する特徴点の両方が不要な特徴点として削除される。第1条件、第2条件及び第3条件のうちZw≧H2によって規定される非検出領域NA2は、X座標Xwの範囲が-(W1/2+W2)~(W1/2-W2)、Y座標Ywの範囲が0~L1、Z座標ZwがH2以上となる領域といえる。
(2-1)カウンタウェイト15に加えて、ミラー18及び支持部19が障害物として検出されることを抑制している。複数の部材が検出可能領域CAに入り込んでいる場合であっても、複数の部材に対して非検出領域NA1,NA2を設定することで、複数の部材のそれぞれを障害物とみなすことなく、検出領域DAの障害物を検出できる。
○各実施形態において、非検出領域NA1は、ワールド座標系のXY平面上での座標を示す2次元座標で規定されていてもよい。即ち、各実施形態における第3条件を削除し、第1条件及び第2条件に合致する特徴点を削除するようにしてもよい。この場合、Z座標Zwに関わらず、X座標Xw及びY座標Ywで規定される非検出領域に存在する特徴点が不要な特徴点として削除される。
このように、ステレオカメラ31の設置位置の変更などによりワールド座標系の座標軸が実施形態から変更された場合、各条件はこれに合わせて変更される。
○各実施形態において、位置検出部は、複数の装置によって構成されていてもよい。例えば、位置検出部は、非検出部として機能する装置と、検出部として機能する装置と、座標導出部として機能する装置と、を個別に備えていてもよい。
○各実施形態において、障害物検出装置30は、位置検出装置41の記憶部43に記憶されている情報など、種々の情報を記憶するように構成された補助記憶装置を備えていてもよい。補助記憶装置としては、例えば、ハードディスクドライブ、ソリッドステートドライブ、EEPROM:Electrically Erasable Programmable Read Only Memory等の、データを書き換え可能な不揮発性記憶装置が用いられる。
○各実施形態において、ステレオカメラ31は、荷役装置17等、どのような位置に取り付けられていてもよい。
DA…検出領域
NA1,NA2…非検出領域
10…移動体としてのフォークリフト
15…フォークリフトの一部であるカウンタウェイト
18…フォークリフトの一部であるミラー
19…フォークリフトの一部である支持部
30…障害物検出装置
31…センサとしてのステレオカメラ
41…位置検出部、非検出部、検出部及び座標導出部としての位置検出装置
Claims (5)
- 移動体に搭載される障害物検出装置であって、
障害物を検出するためのセンサと、
前記センサの検出結果から前記障害物の位置を検出する位置検出部と、を備え、
前記位置検出部は、
前記センサによって前記障害物を検出可能な検出可能領域に予め設定された領域であって前記移動体の一部が存在する領域を非検出領域とすると、前記非検出領域には前記センサの検出結果に関わらず前記障害物が存在しないと判断する非検出部と、
前記検出可能領域のうち前記非検出領域とは異なる領域である検出領域に存在する前記障害物の位置を検出する検出部と、を備える障害物検出装置。 - 前記移動体はフォークリフトであり、
前記非検出領域は、前記フォークリフトのカウンタウェイトが存在する位置に設定されている請求項1に記載の障害物検出装置。 - 前記位置検出部は、水平方向のうち一方向の軸をX軸、水平方向のうち前記X軸に直交する方向の軸をY軸、前記X軸及び前記Y軸に直交する方向の軸をZ軸とする実空間上の座標系での前記障害物の座標を導出する座標導出部を備える請求項1又は請求項2に記載の障害物検出装置。
- 前記非検出領域は、前記実空間上の座標系で前記移動体の一部が存在する領域を示す3次元座標で規定されている請求項3に記載の障害物検出装置。
- 移動体に搭載されており、かつ、センサと位置検出部とを備える障害物検出装置によって障害物の位置を検出する障害物検出方法であって、
前記位置検出部が、前記センサの検出結果を取得するステップと、
前記センサによって前記障害物を検出可能な検出可能領域に予め設定された領域であって前記移動体の一部が存在する領域を非検出領域とすると、前記位置検出部が、前記非検出領域には前記センサの検出結果に関わらず前記障害物が存在しないと判断するステップと、
前記位置検出部が、前記検出可能領域のうち前記非検出領域とは異なる領域である検出領域に存在する前記障害物の位置を検出するステップと、を含む障害物検出方法。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP21831582.8A EP4177694A4 (en) | 2020-07-02 | 2021-06-22 | OBSTACLE DETECTION DEVICE AND OBSTACLE DETECTION METHOD |
CN202180045638.5A CN115720569A (zh) | 2020-07-02 | 2021-06-22 | 障碍物检测装置和障碍物检测方法 |
CA3184206A CA3184206A1 (en) | 2020-07-02 | 2021-06-22 | Obstacle detector device and obstacle detection method |
US18/013,194 US20230264938A1 (en) | 2020-07-02 | 2021-06-22 | Obstacle detector and obstacle detection method |
KR1020227045118A KR20230015429A (ko) | 2020-07-02 | 2021-06-22 | 장해물 검출 장치 및 장해물 검출 방법 |
AU2021301647A AU2021301647A1 (en) | 2020-07-02 | 2021-06-22 | Obstacle detection device and obstacle detection method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020114903A JP7409240B2 (ja) | 2020-07-02 | 2020-07-02 | 障害物検出装置及び障害物検出方法 |
JP2020-114903 | 2020-07-02 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022004495A1 true WO2022004495A1 (ja) | 2022-01-06 |
Family
ID=79316197
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/023647 WO2022004495A1 (ja) | 2020-07-02 | 2021-06-22 | 障害物検出装置及び障害物検出方法 |
Country Status (9)
Country | Link |
---|---|
US (1) | US20230264938A1 (ja) |
EP (1) | EP4177694A4 (ja) |
JP (1) | JP7409240B2 (ja) |
KR (1) | KR20230015429A (ja) |
CN (1) | CN115720569A (ja) |
AU (1) | AU2021301647A1 (ja) |
CA (1) | CA3184206A1 (ja) |
TW (1) | TWI808434B (ja) |
WO (1) | WO2022004495A1 (ja) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7159083B2 (ja) * | 2019-03-06 | 2022-10-24 | 株式会社クボタ | 作業車両 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014097867A (ja) * | 2012-11-14 | 2014-05-29 | Sumitomo Heavy Industries Material Handling Systems Co Ltd | ジブクレーン |
WO2016174977A1 (ja) * | 2015-04-28 | 2016-11-03 | 株式会社小松製作所 | 作業機械の周辺監視装置及び作業機械の周辺監視方法 |
JP2016206801A (ja) | 2015-04-17 | 2016-12-08 | 株式会社リコー | 物体検出装置、移動体機器制御システム及び物体検出用プログラム |
JP2019174347A (ja) * | 2018-03-29 | 2019-10-10 | ヤンマー株式会社 | 障害物検知システム |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6844508B2 (ja) * | 2017-11-15 | 2021-03-17 | 株式会社豊田自動織機 | 安全装置 |
JP6923480B2 (ja) * | 2018-03-29 | 2021-08-18 | ヤンマーパワーテクノロジー株式会社 | 障害物検知システム |
CN111886518A (zh) * | 2018-03-29 | 2020-11-03 | 洋马动力科技有限公司 | 障碍物检测***以及作业车辆 |
-
2020
- 2020-07-02 JP JP2020114903A patent/JP7409240B2/ja active Active
-
2021
- 2021-06-11 TW TW110121405A patent/TWI808434B/zh active
- 2021-06-22 CA CA3184206A patent/CA3184206A1/en active Pending
- 2021-06-22 KR KR1020227045118A patent/KR20230015429A/ko unknown
- 2021-06-22 US US18/013,194 patent/US20230264938A1/en active Pending
- 2021-06-22 WO PCT/JP2021/023647 patent/WO2022004495A1/ja active Application Filing
- 2021-06-22 AU AU2021301647A patent/AU2021301647A1/en active Pending
- 2021-06-22 CN CN202180045638.5A patent/CN115720569A/zh active Pending
- 2021-06-22 EP EP21831582.8A patent/EP4177694A4/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014097867A (ja) * | 2012-11-14 | 2014-05-29 | Sumitomo Heavy Industries Material Handling Systems Co Ltd | ジブクレーン |
JP2016206801A (ja) | 2015-04-17 | 2016-12-08 | 株式会社リコー | 物体検出装置、移動体機器制御システム及び物体検出用プログラム |
WO2016174977A1 (ja) * | 2015-04-28 | 2016-11-03 | 株式会社小松製作所 | 作業機械の周辺監視装置及び作業機械の周辺監視方法 |
JP2019174347A (ja) * | 2018-03-29 | 2019-10-10 | ヤンマー株式会社 | 障害物検知システム |
Non-Patent Citations (1)
Title |
---|
See also references of EP4177694A4 |
Also Published As
Publication number | Publication date |
---|---|
CN115720569A (zh) | 2023-02-28 |
AU2021301647A1 (en) | 2023-02-02 |
KR20230015429A (ko) | 2023-01-31 |
JP2022012811A (ja) | 2022-01-17 |
EP4177694A1 (en) | 2023-05-10 |
JP7409240B2 (ja) | 2024-01-09 |
EP4177694A4 (en) | 2023-12-20 |
TW202203155A (zh) | 2022-01-16 |
US20230264938A1 (en) | 2023-08-24 |
TWI808434B (zh) | 2023-07-11 |
CA3184206A1 (en) | 2022-01-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR20190095592A (ko) | 라이다 센서 및 카메라를 이용한 객체 검출 방법 및 그를 위한 장치 | |
EP3716145A1 (en) | Object detection device and method | |
EP3633619B1 (en) | Position detection apparatus and position detection method | |
JP7180445B2 (ja) | 物体検出装置 | |
WO2022004495A1 (ja) | 障害物検出装置及び障害物検出方法 | |
CN112611360B (zh) | 物体检测装置、车辆及物体检测处理方法 | |
US20230237809A1 (en) | Image processing device of person detection system | |
JP6171608B2 (ja) | 物体検出装置 | |
JP6114572B2 (ja) | 対象物領域推定方法、対象物領域推定装置およびそれを備えた対象物検出装置、車両。 | |
US20230237830A1 (en) | Image processing device of person detection system | |
JP7081526B2 (ja) | 物体検出装置 | |
JP7014122B2 (ja) | 物体検出装置及び物体検出方法 | |
JP2022094178A (ja) | 産業車両 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21831582 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20227045118 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 3184206 Country of ref document: CA |
|
ENP | Entry into the national phase |
Ref document number: 2021301647 Country of ref document: AU Date of ref document: 20210622 Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2021831582 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2021831582 Country of ref document: EP Effective date: 20230202 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |