TWI821089B - Traffic road intelligent detection system and edge collection device - Google Patents
Traffic road intelligent detection system and edge collection device Download PDFInfo
- Publication number
- TWI821089B TWI821089B TW111150396A TW111150396A TWI821089B TW I821089 B TWI821089 B TW I821089B TW 111150396 A TW111150396 A TW 111150396A TW 111150396 A TW111150396 A TW 111150396A TW I821089 B TWI821089 B TW I821089B
- Authority
- TW
- Taiwan
- Prior art keywords
- data
- edge
- road surface
- unit
- inertial
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000005259 measurement Methods 0.000 claims description 46
- 238000012549 training Methods 0.000 claims description 35
- 230000005540 biological transmission Effects 0.000 claims description 15
- 238000010801 machine learning Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000013136 deep learning model Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000013210 evaluation model Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 241000270722 Crocodylidae Species 0.000 claims 1
- LNNWVNGFPYWNQE-GMIGKAJZSA-N desomorphine Chemical compound C1C2=CC=C(O)C3=C2[C@]24CCN(C)[C@H]1[C@@H]2CCC[C@@H]4O3 LNNWVNGFPYWNQE-GMIGKAJZSA-N 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000000034 method Methods 0.000 description 8
- 238000005336 cracking Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 241000270728 Alligator Species 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000004901 spalling Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
本發明係涉及一種交通路面智慧檢測系統及邊緣收集裝置,其主要以邊緣端行動裝置來錄影分析框選道路的PCI鋪面特徵的MP4及其所對應F-IMU值、B-IMU值及GPS之數據成數個後設資料(metadata),再將該數個後設資料分別上傳至一雲端伺服器後,再由該雲端伺服器所建置的一路面辨識模組依據各個後設資料,分別辨識出一PCI鋪面狀況指標的特徵值並儲存之,最後再將辨識結果資訊會依據GPS位置資訊而顯示於一地理資訊系統上,以利於交通道路管理人員及養護人員查詢。 The invention relates to a traffic road intelligent detection system and an edge collection device, which mainly uses an edge-end mobile device to record and analyze the MP4 of the PCI pavement characteristics of the selected road and its corresponding F-IMU value, B-IMU value and GPS. The data is converted into several metadata, and then the metadata are uploaded to a cloud server respectively, and then a road surface recognition module built by the cloud server recognizes the data respectively based on each metadata. The characteristic value of a PCI pavement condition indicator is generated and stored. Finally, the identification result information will be displayed on a geographical information system based on the GPS location information to facilitate inquiries by traffic road management personnel and maintenance personnel.
Description
本發明關於交通道路管理技術領域,尤指一種交通路面智慧檢測系統及邊緣收集裝置之範疇。 The present invention relates to the technical field of traffic road management, and in particular, to the category of a traffic road intelligent detection system and an edge collection device.
按,「路平、燈亮、水溝通」一直是各縣市政府皆致力達成的公共需求,其中,路平又是訴求之首。但現行一般路平養護是採人工目視定期巡檢、民眾申訴等二種方式來進行,而現有的路檢設備不是「非常貴」就是「非常複雜」,如本國新型專利第TWM386314U號「道路檢測車之鋪面平坦度量測單元」。 According to reports, "flat roads, bright lights, and water connections" have always been public needs that all counties and municipal governments are striving to achieve, and among them, smooth roads are at the top of the list. However, the current general road level maintenance is carried out by two methods: manual visual inspections and public complaints. The existing road inspection equipment is either "very expensive" or "very complicated". For example, the country's new patent No. TWM386314U "Road Inspection Vehicle pavement flatness measurement unit".
路面狀況代表著許多人或車的用路安全,等到民眾申訴,往往已經非常嚴重或有交通意外發生。因此,本發明人希望能找一個方式,讓道路養護主管單位能精確找出需整修的路段,讓人民對路平維護更有感。 Road condition represents the safety of many people or vehicles. By the time people complain, it is often very serious or traffic accidents have occurred. Therefore, the inventor hopes to find a way to allow the road maintenance authority to accurately identify the road sections that need to be repaired, so that the people can be more aware of road maintenance.
緣此,為了能夠配合智慧生活、智慧城市的開發,於是本發明人乃窮極心思開發出一種「交通路面智慧檢測系統及邊緣收集裝置」,故本發明之主要目的在於:提供低成本建置的一種交通路面智慧檢測系統及邊緣收集裝置;而本發明之次要目的:在於提供提升交通道路鋪面辨識精準度的一種交通路面智慧檢測系統其邊緣收集裝置。 Therefore, in order to cooperate with the development of smart life and smart cities, the inventor has put great effort into developing a "traffic road intelligent detection system and edge collection device". Therefore, the main purpose of the present invention is to provide a low-cost construction A traffic road surface intelligent detection system and an edge collection device; and the secondary purpose of the present invention is to provide an edge collection device of a traffic road surface intelligent detection system that improves the accuracy of traffic road pavement identification.
為了達到上述目的,本發明運用如下技術手段,一種邊緣收集裝置,其包含有:一邊緣端行動裝置,係裝置於一移動載具的前端處,且該邊緣端 行動裝置更包含有一鏡頭單元、一顯示單元、一GPS定位單元、一前慣性測量單元、一記憶體單元及一通信單元分別電性連接一運算處理器;其中該前慣性測量單元提供量測該移動載具的前端處的姿態角、加速度及地球磁場的絕對指向之前慣性姿態數據資料;一慣性測量裝置,係裝置於該移動載具的後端處且更包含有一後慣性測量單元及一傳輸單元;其中該後慣性測量單元提供量測該移動載具的後端處的姿態角、加速度及地球磁場的絕對指向之後慣性姿態數據資料,而該傳輸單元則將該後慣性姿態數據資料輸送至該邊緣端行動裝置;及一整合應用程式單元,係預存至該邊緣端行動裝置的記憶體單元,並由該運算處理器呼叫執行以針對一不良路面進行錄影並框出PCI鋪面特徵而成一串流影音,再將該串流影音、前慣性姿態數據、後慣性姿態數據、GPS資訊之後設資料儲存並同時藉由該邊緣端行動裝置上傳到雲端,且以其中部分後設資料提供作為雲端所設一路面辨識模組進行機器學習之訓練樣本。 In order to achieve the above object, the present invention uses the following technical means, an edge collection device, which includes: an edge end mobile device, which is installed at the front end of a mobile carrier, and the edge end The mobile device further includes a lens unit, a display unit, a GPS positioning unit, a front inertial measurement unit, a memory unit and a communication unit electrically connected to a computing processor respectively; wherein the front inertial measurement unit provides measurement of the The attitude angle, acceleration and absolute pointing of the earth's magnetic field at the front end of the mobile vehicle are the previous inertial attitude data data; an inertial measurement device is installed at the rear end of the mobile vehicle and further includes a rear inertial measurement unit and a transmission unit; wherein the rear inertial measurement unit provides inertial attitude data after measuring the attitude angle, acceleration and absolute pointing of the earth's magnetic field at the rear end of the mobile vehicle, and the transmission unit transmits the rear inertial attitude data to The edge-end mobile device; and an integrated application unit are pre-stored in the memory unit of the edge-end mobile device and are called and executed by the computing processor to record a bad road surface and frame a series of PCI pavement features. Stream video and audio, and then store the streaming video, front inertial attitude data, rear inertial attitude data, and GPS information and upload it to the cloud through the edge mobile device, and provide part of the metadata as a cloud Set up a road surface recognition module to carry out training samples for machine learning.
上述該邊緣收集裝置,係提供針對交通道路的該數個串流影音分別以Tensorflow開發軟體的物件偵測進行初步辨識並框選出一PCI鋪面特徵並同時記錄其GPS、前慣性姿態、後慣性姿態之數據來結合成數個後設資料。 The above-mentioned edge collection device provides several streaming videos for traffic roads and uses Tensorflow development software to perform preliminary identification on object detection and selects a PCI pavement feature and simultaneously records its GPS, front inertial attitude, and rear inertial attitude. The data is combined into several metadata.
另關於本發明一種交通路面智慧檢測系統,其包含有:一邊緣端行動裝置,係裝置於一移動載具的前端處,且該邊緣端行動裝置更包含有一鏡頭單元、一顯示單元、一GPS定位單元、一前慣性測量單元、一記憶體單元及一通信單元分別電性連接一運算處理器;其中該前慣性測量單元提供量測該移動載具的前端處的姿態角、加速度及地球磁場的絕對指向之前慣性姿態數據資料;一慣性測量裝置,係裝置於該移動載具的後端處且更包含有一後慣性測量單元及一傳輸單元;其中該後慣性測量單元提供量測該移動載具的後端處的姿 態角、加速度及地球磁場的絕對指向之後慣性姿態數據資料,而該傳輸單元則將該後慣性姿態數據資料輸送至該邊緣端行動裝置;一整合應用程式單元,係預存至該邊緣端行動裝置的記憶體單元,並由該運算處理器呼叫執行以針對一不良路面進行錄影並框出PCI鋪面特徵而成一串流影音,再將該串流影音、前慣性姿態數據、後慣性姿態數據、GPS資訊之後設資料儲存並同時藉由該邊緣端行動裝置上傳到雲端,且以其中部分後設資料提供作為雲端所設一路面辨識模組進行機器學習之訓練樣本;及一雲端伺服器,係接收該邊緣端行動裝置所傳來的串流影音、慣性姿態、GPS資訊之數據,且該雲端伺服器更包含有經過機器學習所建立該路面辨識模組,而該路面辨識模組會依據邊緣端所傳來的各已框選的PCI鋪面特徵的影音串流及其所對應的慣性姿態之數據來分別辨識出不良路面的PCI鋪面狀況指標的特徵值並儲存,最終辨識結果會提供藉由該GPS資訊輸出顯示於一地理資訊系統上。 In addition, the present invention relates to a traffic road intelligent detection system, which includes: an edge-end mobile device installed at the front end of a mobile vehicle, and the edge-end mobile device further includes a lens unit, a display unit, and a GPS The positioning unit, a front inertial measurement unit, a memory unit and a communication unit are electrically connected to a computing processor respectively; the front inertial measurement unit provides measurement of the attitude angle, acceleration and earth's magnetic field at the front end of the mobile vehicle. The absolute pointing previous inertial attitude data; an inertial measurement device is installed at the rear end of the mobile vehicle and further includes a rear inertial measurement unit and a transmission unit; wherein the rear inertial measurement unit provides measurement of the mobile vehicle posture at the rear end of the tool The post-inertial attitude data data of the state angle, acceleration and absolute pointing of the earth's magnetic field are collected, and the transmission unit transmits the post-inertial attitude data data to the edge-end mobile device; an integrated application unit is pre-stored to the edge-end mobile device The memory unit is called and executed by the computing processor to record a bad road surface and frame the PCI pavement features to form a streaming video, and then combine the streaming video, front inertial attitude data, rear inertial attitude data, and GPS The information is then stored and uploaded to the cloud through the edge mobile device at the same time, and part of the metadata is used as a training sample for machine learning for a road surface recognition module set in the cloud; and a cloud server receives The edge terminal mobile device transmits streaming video, inertial attitude, and GPS information data, and the cloud server further includes the road surface recognition module created through machine learning, and the road surface recognition module will be based on the edge terminal The transmitted audio and video streams of the selected PCI pavement characteristics and their corresponding inertial posture data are used to identify and store the characteristic values of the PCI pavement condition indicators of the bad road surfaces. The final identification results will be provided through the GPS information output is displayed on a geographic information system.
該路面辨識模組係使用由Tensorflow開發軟體所開發的該路面辨識模組並以scikit-learn作為機器學習的函式庫來進行資料前處理與建立模型,且該路面辨識模組會依據交通道路之不良路面的後設資料,分別辨識出不良路面的該數個串流影音的鋪面狀況指標的特徵值並作儲存。 The road surface recognition module uses the road surface recognition module developed by Tensorflow development software and uses scikit-learn as the machine learning function library to perform data preprocessing and build models, and the road surface recognition module will be based on traffic roads. The metadata of the bad road surface is used to identify and store the characteristic values of the pavement condition indicators of the plurality of streaming videos on the bad road surface.
其中該路面辨識模組係採用監督式深度學習模型框架,並使用以YOLO演算法所識別數個不良路面串流影音的鋪面狀況指標的特徵值及其所對應的前慣性姿態、後慣性姿態等數據來作為監督式學習的一訓練樣本之標記檔,進而讓該鋪面狀況指標的特徵值與前慣性姿態數據、後慣性姿態數據產生對應關聯,以增進不良路面的辨識效果。 The road surface recognition module adopts a supervised deep learning model framework, and uses the YOLO algorithm to identify the characteristic values of pavement condition indicators of several bad road streaming videos and their corresponding front inertia posture, rear inertia posture, etc. The data is used as a mark file of a training sample for supervised learning, and then the characteristic value of the pavement condition indicator is correspondingly associated with the front inertial attitude data and the rear inertial attitude data to improve the identification of bad road surfaces.
其中該路面辨識模組的訓練及測試係依序經過一資料前處理步驟、一建構機器學習模型並訓練步驟、一評估模型步驟及一預測步驟,而在該資料前處理步驟中將訓練樣本區分為一75%訓練集及一25%測試集。 The training and testing of the road surface recognition module sequentially go through a data pre-processing step, a machine learning model construction and training step, an evaluation model step and a prediction step, and in the data pre-processing step the training samples are distinguished It is a 75% training set and a 25% test set.
其中該訓練樣本的標記檔更包含有GPS的速度數據。 The mark file of the training sample also contains GPS speed data.
其中該訓練樣本的標記檔更包含有GPS的速度數據。 The mark file of the training sample also contains GPS speed data.
其中該鋪面狀況指標的特徵值依據ASTM D6433-11所定義之破壞項目合計共有19項破壞,分別為鱷魚狀裂縫、冒油、塊狀裂縫、凸與凹陷、波浪型路面、凹陷、邊緣裂縫、反射裂縫、路肩高差、縱與橫裂縫、補錠、粒料光滑、坑洞、跨越鐵道、車轍、推擠、滑動裂縫、***及風化與剝脫。 Among them, the characteristic value of the pavement condition index is based on the damage items defined by ASTM D6433-11. There are a total of 19 damages, including alligator cracks, oil leakage, block cracks, convexities and depressions, wavy pavement, depressions, edge cracks, Reflective cracks, shoulder height differences, longitudinal and transverse cracks, patches, granular smoothing, potholes, railroad crossings, ruts, jostling, sliding cracks, bulges, and weathering and spalling.
據此,本發明藉由上述技術手段,可以達到如下功效: Accordingly, through the above technical means, the present invention can achieve the following effects:
1.本發明整套系統設備僅包含有一移動載具、一雲端伺服器、一邊緣端行動裝置、一AI影像路面辨識模組等,且採用邊緣運算架構,分擔雲端伺服器的運算負擔,故整套系統建置成本低,又可以協助提供路面驗收及快速判斷路面情況。 1. The entire system equipment of the present invention only includes a mobile vehicle, a cloud server, an edge mobile device, an AI image road recognition module, etc., and adopts an edge computing architecture to share the computing burden of the cloud server, so the entire system The system has low construction cost and can assist in providing road surface acceptance and quick judgment of road conditions.
2.本發明的路面辨識模組係採用監督式的深度學習模型框架,且以前慣性姿態、後慣性姿態及PCI鋪面狀況指標的特徵值以作為不良路面影像辨識之訓練樣本的標記檔,所訓練出來的路面辨識模組具有高精準的辨識效果。 2. The road surface recognition module of the present invention adopts a supervised deep learning model framework, and the characteristic values of the previous inertial attitude, the rear inertial attitude and the PCI pavement condition indicator are used as the mark file of the training sample for bad road image recognition. The road surface recognition module produced has high-precision recognition effect.
A:交通路面智慧檢測方法 A: Traffic road intelligent detection method
a、b、c、d、e:步驟 a, b, c, d, e: steps
B:交通路面智慧檢測系統 B: Traffic road intelligent detection system
C:移動載具 C:Mobile vehicle
C1:手機架 C1: mobile phone holder
1:邊緣端行動裝置 1: Edge mobile devices
11:鏡頭單元 11: Lens unit
12:顯示單元 12:Display unit
13:GPS定位單元 13:GPS positioning unit
14:前慣性測量單元 14: Front inertial measurement unit
15:記憶體單元 15:Memory unit
16:通信單元 16: Communication unit
17:運算處理器 17:Arithmetic processor
2:慣性測量裝置 2: Inertial measurement device
21:後慣性測量單元 21:Rear inertial measurement unit
22:傳輸單元 22:Transmission unit
3:整合應用程式單元 3: Integrate application units
4:雲端伺服器 4:Cloud server
41:路面辨識模組 41: Pavement recognition module
5:地理資訊系統 5:Geographic information system
〔圖1〕本發明「交通路面智慧檢測方法」之步驟流程圖。 [Figure 1] The step flow chart of the "intelligent traffic road detection method" of the present invention.
〔圖2〕本發明「交通路面智慧檢測系統」架構之示意圖。 [Figure 2] Schematic diagram of the architecture of the "intelligent traffic road detection system" of the present invention.
〔圖3〕本發明「移動載具」選用機車行駛於路面之錄影角度之示意圖。 [Figure 3] A schematic diagram of the video recording angle of a motorcycle traveling on the road for the "mobile vehicle" of the present invention.
〔圖4〕本發明「移動載具」選用汽車行駛於路面之錄影角度之示意圖。 [Figure 4] A schematic diagram of the video recording angle of a car driving on the road for the "mobile vehicle" of the present invention.
〔圖5〕本發明「邊緣端行動裝置」框選不良路鋪面特徵並記錄其對應的GPS、F-IMU值、B-IMU值、MP4數據之作動示意圖。 [Figure 5] Schematic diagram of the operation of the "edge mobile device" of the present invention to select bad road pavement features and record their corresponding GPS, F-IMU values, B-IMU values, and MP4 data.
〔圖6〕本發明「交通路面智慧檢測系統」之運作流程圖。 [Figure 6] The operation flow chart of the "intelligent traffic road detection system" of the present invention.
〔圖7〕本發明「雲端伺服器的影像辨識模組」演算及其建置之流程圖。 [Figure 7] The flow chart of the calculation and construction of the "image recognition module of the cloud server" of the present invention.
〔圖8〕本發明「雲端伺服器的影像辨識模組」演算及其建置之實際流程圖。 [Figure 8] The actual flow chart of the calculation and construction of the "Image Recognition Module of Cloud Server" of the present invention.
〔圖9〕本發明「邊緣端行動裝置」架構之示意圖。 [Figure 9] Schematic diagram of the architecture of the "edge mobile device" of the present invention.
〔圖10〕本發明「慣性測量裝置」架構之示意圖。 [Figure 10] Schematic diagram of the structure of the "inertial measurement device" of the present invention.
〔圖11〕本發明關於不良路面之鋪面示意圖。 [Figure 11] A schematic diagram of the pavement of poor road surface according to the present invention.
〔圖12〕本發明關於「前慣性測量數據」及「後慣性測量數據」之示意圖。 [Fig. 12] A schematic diagram of the "front inertia measurement data" and "rear inertia measurement data" of the present invention.
〔圖13〕本發明關於腳本式事件反應流程之示意圖。 [Figure 13] Schematic diagram of the scripted event response process of the present invention.
本發明係關於一種交通路面智慧檢測系統及邊緣收集裝置,其主要提供低成本的建置系統,以精準地辨識交通道路不良路面的狀況,來協助路面驗收、養護人快速判斷路面情況,而有利於通知養護單位來進行道路維護養護;一種交通路面智慧檢測方法A,如圖1所示,其包含有:一邊緣端資料蒐集步驟a、一邊緣端不良路面偵測框選步驟b、一數據資訊上傳雲端步驟c、一雲端不良路面辨識步驟d;茲將上述各步驟配合圖1及圖2,分別說明如後。 The invention relates to a traffic road surface intelligent detection system and edge collection device. It mainly provides a low-cost construction system to accurately identify the condition of bad road surfaces on traffic roads, to assist road acceptance and maintenance personnel to quickly judge the road conditions, and is beneficial To notify the maintenance unit to perform road maintenance; a traffic road intelligent detection method A, as shown in Figure 1, which includes: an edge end data collection step a, an edge end bad road surface detection frame selection step b, and a data Step c of uploading information to the cloud, and step d of identifying bad road surface in the cloud; each of the above steps is explained below with reference to Figures 1 and 2.
所述該邊緣端資料蒐集步驟a,如圖3及圖4所示,係藉由至少一個或數個邊緣端行動裝置蒐集交通各道路不良路面的數個串流影音(可以是AVI、WMV、MOV、MP4、RM等格式,以下統稱MP4)及所對應的一前慣性姿 態、一後慣性姿態、一GPS資訊之數據資訊;其中各道路不良路面的數個串流影音的較佳錄影長度大約為150公分長的不良路面。 The edge end data collection step a, as shown in Figure 3 and Figure 4, is to collect several streaming videos (which can be AVI, WMV, MOV, MP4, RM and other formats (hereinafter collectively referred to as MP4) and the corresponding forward inertial posture The data information includes the attitude, the inertial attitude, and the GPS information; among them, the optimal recording length of several streaming videos on the bad road surface of each road is about 150 centimeters long on the bad road surface.
即本步驟a主要由一移動載具C的前端、後端分別安裝有一邊緣端行動裝置1、一慣性測量裝置2後,其中移動載具C較佳則選用機車,次佳則為汽車,而邊緣端行動裝置1較佳則選用智慧型手機(或使用平板電腦、與鏡頭分離之裝置,例如:以一筆電配合一攝影鏡頭等裝置),其中所謂慣性姿態(inertial attitude)之數據係由慣性測量單元(Inertial Measurement Unit,簡稱IMU)所感測到一物體的三軸姿態角、三軸加速度及三軸地球磁場的絕對指向之數據;故前慣性姿態係指該移動載具C的前端的慣性姿態,本發明將其稱F-IMU值;而後慣性姿態係指該移動載具C的後端的慣性姿態,本發明將其稱B-IMU值。 That is, this step a mainly consists of installing an edge-end mobile device 1 and an inertial measurement device 2 on the front and rear ends of a mobile vehicle C. The best choice for mobile vehicle C is a motorcycle, the second best is a car, and the edge-end The mobile device 1 is preferably a smart phone (or a tablet computer or a device separated from the lens, such as a laptop with a camera lens), in which the so-called inertial attitude data is obtained by an inertial measurement unit ( Data on the three-axis attitude angle, three-axis acceleration and the absolute direction of the three-axis earth's magnetic field sensed by the Inertial Measurement Unit (IMU); therefore, the front inertial attitude refers to the inertial attitude of the front end of the mobile vehicle C. The invention calls this the F-IMU value; the rear inertial attitude refers to the inertial attitude of the rear end of the mobile vehicle C, and the invention calls it the B-IMU value.
當該移動載具C行駛於道路上以進行不良路面攝影並記錄當下的F-IMU值、B-IMU值、GPS之數據,其中該F-IMU值、該GPS之數據係由該邊緣端行動裝置1負責感測蒐集,而該B-IMU值數據係由該慣性測量裝置2負責感測蒐集,蒐集後的該B-IMU值數據經由無線或有線傳輸傳送到該邊緣端行動裝置1。 When the mobile vehicle C is driving on the road to take pictures of bad road surfaces and record the current F-IMU value, B-IMU value, and GPS data, the F-IMU value and the GPS data are processed by the edge terminal. Device 1 is responsible for sensing and collecting, and the inertial measurement device 2 is responsible for sensing and collecting the B-IMU value data. The collected B-IMU value data is transmitted to the edge mobile device 1 through wireless or wired transmission.
所述該邊緣端不良路面偵測框選步驟b,如圖5所示,係針對交通道路的該數個串流影音(MP4)分別以Tensorflow開發軟體的物件偵測(Object detector)進行初步辨識並框選(Bounding Box)出一PCI鋪面特徵並同時分別記錄其GPS、F-IMU值、B-IMU值之數據來結合成數個後設資料(metadata);特別一提,該物件偵測(Object detector)係為Tensorflow開發軟體的一個物件辨識功能。 The edge edge bad road surface detection frame selection step b, as shown in Figure 5, uses the object detector of the Tensorflow development software for preliminary identification of the several streaming videos (MP4) on the traffic road. And Bounding Box selects a PCI pavement feature and simultaneously records its GPS, F-IMU value, and B-IMU value data to combine into several metadata; in particular, the object detection ( Object detector) is an object identification function of Tensorflow development software.
所述數據資訊上傳雲端步驟c,如圖6所示,係整合前步驟針對交通道路的不良路面所蒐集到的數個後設資料分別上傳至雲端伺服器4作儲存。 The data information is uploaded to the cloud in step c, as shown in Figure 6. The system integrates the previous steps and uploads several metadata collected for the bad road surface of the traffic road to the cloud server 4 for storage.
所述該雲端不良路面辨識步驟d,如圖7及圖8所示,係在該雲端伺服器4更包含有由Tensorflow開發軟體所開發的一路面辨識模組41並以scikit-learn作為機器學習的函式庫來進行資料前處理與建立模型,且該路面辨識模組41會依據交通道路之不良路面的數個後設資料,分別辨識出不良路面的該數個串流影音的鋪面狀況指標(Pavement Condition Index,簡稱PCI)的特徵值並作儲存,而不良路面的PCI指標的特徵值係依據ASTM D6433-11所定義之破壞項目合計共有四大種類及19項破壞,分別為NO.01鱷魚狀裂縫(Alligator Craking)、NO.02冒油(Bleeding)、NO.03塊狀裂縫(Block Cracking)、NO.04凸與凹陷(Bumps and Sags)、NO.05波浪型路面(Corrugation)、NO.06凹陷(Depression)、NO.07邊緣裂縫(Edge Cracking)、NO.08反射裂縫(Jt.Reflection Cracking)、NO.09路肩高差(Lane/Shoulder Drop Off)、NO.10縱與橫裂縫(Long & Trans Cracking)、NO.11補錠(Patching & Util Cut Patching)、NO.12粒料光滑(Polished Aggregate)、NO.13坑洞(Potholes)、NO.14跨越鐵道(Railroad crossing)、NO.15車轍(Rutting)、NO.16推擠(Shoving)、NO.17滑動裂縫(Slippage Cracking)、NO.18***(Swell)、NO.19風化與剝脫(Weathering/Raveling),如底下表1所示者。 The cloud bad road surface identification step d, as shown in Figures 7 and 8, is that the cloud server 4 further includes a road surface identification module 41 developed by Tensorflow development software and uses scikit-learn as machine learning A function library is used to perform data preprocessing and build models, and the road surface identification module 41 will respectively identify the pavement condition indicators of the several streaming videos of the bad road surface based on several metadata of the bad road surface of the traffic road. (Pavement Condition Index, PCI for short) characteristic values are stored, and the characteristic values of the PCI index of bad pavement are based on the damage items defined by ASTM D6433-11. There are four major categories and 19 types of damage, respectively NO.01 Alligator Craking, NO.02 Bleeding, NO.03 Block Cracking, NO.04 Bumps and Sags, NO.05 Corrugation, NO.06 Depression, NO.07 Edge Cracking, NO.08 Reflection Cracking, NO.09 Lane/Shoulder Drop Off, NO.10 Vertical and horizontal Cracks (Long & Trans Cracking), NO.11 Patching & Util Cut Patching, NO.12 Polished Aggregate, NO.13 Potholes (Potholes), NO.14 Railroad crossing , NO.15 Rutting, NO.16 Shoving, NO.17 Slippage Cracking, NO.18 Swell, NO.19 Weathering/Raveling, such as Those shown in Table 1 below.
進一步,在本步驟d中,該路面辨識模組41係採用監督式深度學習模型(deep learning modle)框架,並使用以YOLO演算法所識別數個不良路面的串流影音的鋪面狀況指標的特徵值及其所對應的F-IMU值、B-IMU值等數據來作為監督式學習(supervised learning)的訓練樣本(training sample)之標記檔(label),進而讓該路面辨識模組41可以辨識該鋪面狀況指標的特徵值與F-IMU值、B-IMU值等之數據產生對應關聯,以增進交通道路不良路面的辨識效果;進一步,該訓練樣本係由75%訓練集(training data)及25%測試集(testing set)所組成,而該訓練樣本的標記檔可以額外再加人GPS的速度數據之參數,進而提升辨識的精準度。 Further, in this step d, the road surface identification module 41 adopts a supervised deep learning model framework and uses the characteristics of the pavement condition indicators of the streaming videos of several bad road surfaces identified by the YOLO algorithm. The value and its corresponding F-IMU value, B-IMU value and other data are used as the label file (label) of the training sample of supervised learning (supervised learning), so that the road surface recognition module 41 can recognize The characteristic value of the pavement condition index is correspondingly associated with the data of F-IMU value, B-IMU value, etc., to enhance the identification effect of bad road surface on traffic roads; further, the training sample is composed of 75% training set (training data) and It consists of 25% test set, and the marker file of the training sample can be additionally added with the parameters of GPS speed data, thereby improving the accuracy of identification.
特別一提,路面辨識模型在訓練集上進行調適。對於監督式學習,訓練集是由用來調適參數(例如:人工神經網路中神經元之間連結的權重)的範例組成的集合。在實施當中,訓練集通常是由輸入向量(純量)和輸出向量(純量)組成的資料對。其中輸出向量(純量)被稱為目標或標籤。在訓練過程中,當前路面辨識模型會對訓練集中的每個範例進行預測,並將預測結果與目標進行比較。根據比較的結果,學習演算法會更新路面辨識模型的參數。模型調適的過程可能同時包括特徵選擇和參數估計。 In particular, the road surface recognition model is adapted on the training set. For supervised learning, a training set is a collection of examples used to tune parameters (such as the weights of connections between neurons in an artificial neural network). In implementation, the training set is usually a pair of input vectors (scalars) and output vectors (scalars). where the output vector (scalar) is called the target or label. During training, the current road surface recognition model makes predictions for each example in the training set and compares the predictions with the target. Based on the comparison results, the learning algorithm updates the parameters of the road surface recognition model. The process of model tuning may include both feature selection and parameter estimation.
而測試集則被用來提供對最終的路面辨識模模型之無偏評估。 The test set is used to provide an unbiased evaluation of the final road surface identification model.
進一步,該路面辨識模組41的訓練步驟,如圖7及圖8所示,如下述:步驟1:資料前處理 1.以scikit-learn的train test split()函式將樣本資料隨機排序(shuffle)後分成兩部分:75%樣本為訓練集,25%樣本為測式集(可自行設定比例,但以經驗來說,這樣的比例是不錯的);2.stratify=y:依據原目標的分類比例來分層;3.random_state=0:設定整數固定種子值(其他整數亦可),讓每次實驗跑的資料都相同;4.train_test_split()函式回覆4個NumPy陣列;5.#X_train,X_test訓練與測試資料,都是二維陣列,每一列是一筆樣本資料;6.#y_train,y_test訓練與測試答案,都是一維陣列,每一個元素是一個類別資料;步驟2:建構機器學習模型並訓練建立一個機器學習模型,給定訓練資料與答案,利用fit()擬合方法來訓練模型;步驟3:評估模型(Evaluating the model)利用score()方法計算訓練效能:給定測試資料與答案,計算預測正確的比例;及步驟4:預測(prediction)訓練完畢且效能符合標準即可進行預測:給定新資料,利用predict()方法來預測結果。 Further, the training steps of the road surface recognition module 41, as shown in Figures 7 and 8, are as follows: Step 1: Data preprocessing 1. Use scikit-learn's train test split() function to randomly sort (shuffle) the sample data and divide it into two parts: 75% of the samples are the training set, and 25% of the samples are the test set (the proportion can be set by yourself, but based on experience Generally speaking, this ratio is good); 2. stratify=y: Stratify according to the classification ratio of the original target; 3. random_state=0: Set an integer fixed seed value (other integers are also acceptable), so that each experiment can be run The data are the same; 4. The train_test_split() function returns 4 NumPy arrays; 5. #X_train, The test answers are all one-dimensional arrays, and each element is a category data; Step 2: Construct a machine learning model and train it to build a machine learning model. Given the training data and answers, use the fit() fitting method to train the model; Step 3: Evaluating the model uses the score() method to calculate the training efficiency: given the test data and answers, calculate the proportion of correct predictions; and Step 4: Prediction can be made after the training is completed and the performance meets the standards. : Given new data, use the predict() method to predict the results.
因此,在本步驟d中,該路面辨識模組41會藉由訓練樣本經過一連串的訓練、測試及調較,進而取得一個最佳的辨識模型;故該路面辨識模組 41實際的辨識過程中,會將該邊緣端行動裝置1所傳來的MP4檔預先轉換成數個影像後,再分別經降噪後才由該路面辨識模組41進行辨識。 Therefore, in this step d, the road surface recognition module 41 will obtain an optimal recognition model through a series of training, testing and adjustment using training samples; therefore, the road surface recognition module 41 During the actual recognition process, the MP4 files transmitted from the edge mobile device 1 will be converted into several images in advance, and then the images will be recognized by the road surface recognition module 41 after noise reduction.
所述該路面辨識結果輸出步驟e,係依據前步驟的辨識結果資訊會依據GPS的位置資訊顯示於一地理資訊系統5上。 The road surface recognition result output step e is based on the recognition result information of the previous step being displayed on a geographical information system 5 based on the GPS location information.
請參閱圖2、圖3及圖9所示,關於本發明一種交通路面智慧檢測系統B,係由前述交通路面智慧檢測方法A所建置並執行,進而達到本發明之目的,其包含有:一邊緣端行動裝置、一慣性測量裝置2、一整合應用程式單元3及一雲端伺服器4等裝置;茲配合圖式針對上述各裝置分別說明如後。 Please refer to Figures 2, 3 and 9. As for a traffic road intelligent detection system B of the present invention, it is constructed and executed by the aforementioned traffic road intelligent detection method A to achieve the purpose of the present invention, which includes: An edge mobile device, an inertial measurement device 2, an integrated application unit 3 and a cloud server 4 and other devices; the above-mentioned devices are described separately below with reference to the drawings.
所述該邊緣端行動裝置1,如圖9所示,係提供可執行邊緣端運算(edge computing)之裝置,係裝設於一移動載具C的前端處,例如:機車的握把處,且該邊緣端行動裝置1內建更包含有一鏡頭單元11、一顯示單元12、一GPS定位單元13、一前慣性測量單元14、一記憶體單元15及一通信單元16分別電性連接一運算處理器17;其中該鏡頭單元11會對道路的不良路面進行錄影,而該GPS定位單元13則感測該移動載具C的GPS資訊(亦可稱不良路面的GPS資訊);該前慣性測量單元14則感測該移動載具C前端處的F-IMU值,而該記憶體單元15則提供儲存該行動裝置1的整合應用程式單元3,以及MP4、GPS、F-IMU值、B-IMU值等之數個後設資料(metadata);該通信單元16則藉由行動網路、網際網路與該雲端伺服器4耦接後,可上傳該數個後設資料,而該運算處理器17執行該整合應用程式單元3以提供該不良路面之錄影MP4並框選,且同時取得感測後的與該MP4對應的GPS、F-IMU值、B-IMU值,以完成數次後設資料之收集; 進一步,該移動載具C較佳選用如圖3的機車,次佳為如圖4的汽車,且該機車前端的握把處附設有具自動或手動調整角度功能的一手機架C1,該手機架C1離地面高度為0.5~1.6公尺之間,且該移動載具的速度設為低於120km/hr以下,以取得清晰的影像;若使用汽車,則該智慧型手機安裝利地面高度為0.5~1.6公尺之間的保險桿、測後照鏡或擋風玻璃處;而該邊緣端行動裝置1係設為智慧型手機(或使用平板電腦、與鏡頭分離之裝置,例如:以一筆電配合一攝影鏡頭等裝置),並可以裝設於該機車的手機架C1上,且該智慧型手機的鏡頭單元11拍攝道路的角度θ設為22~50度之間;特別一提,機車及智慧型手機均為非常簡便的工具,在騎乘道路的過程中,當人員目視道路有不良路面時,則直接騎向該不良路面處便可對其錄影來取得數個後設資料。 The edge mobile device 1, as shown in Figure 9, is a device that can perform edge computing and is installed at the front end of a mobile vehicle C, such as the handlebar of a motorcycle. The edge mobile device 1 further includes a lens unit 11, a display unit 12, a GPS positioning unit 13, a front inertial measurement unit 14, a memory unit 15 and a communication unit 16 that are each electrically connected to a computing unit. Processor 17; wherein the lens unit 11 records the bad road surface of the road, and the GPS positioning unit 13 senses the GPS information of the mobile vehicle C (which can also be called the GPS information of the bad road surface); the front inertial measurement The unit 14 senses the F-IMU value at the front end of the mobile vehicle C, and the memory unit 15 provides the integrated application unit 3 for storing the mobile device 1, as well as MP4, GPS, F-IMU value, B- Several metadata (metadata) equal to the IMU value; the communication unit 16 is coupled to the cloud server 4 through a mobile network or the Internet, and can upload the several metadata, and the calculation processing The processor 17 executes the integrated application unit 3 to provide the video MP4 of the bad road surface and frame selection, and at the same time obtains the sensed GPS, F-IMU value, and B-IMU value corresponding to the MP4 to complete several times. Collection of information; Furthermore, the mobile vehicle C is preferably a motorcycle as shown in Figure 3, and the second best is a car as shown in Figure 4, and a mobile phone holder C1 with an automatic or manual angle adjustment function is attached to the handle at the front of the motorcycle. The height of C1 from the ground is between 0.5 and 1.6 meters, and the speed of the mobile vehicle is set to less than 120km/hr to obtain clear images; if a car is used, the height of the ground for installing the smartphone is The bumper, rear view mirror or windshield is between 0.5 and 1.6 meters; and the edge mobile device 1 is set as a smartphone (or a tablet computer, a device separated from the lens, for example: using a pen Electrically coupled with a photographic lens or other device), and can be installed on the mobile phone holder C1 of the motorcycle, and the angle θ of the camera unit 11 of the smartphone to capture the road is set to between 22 and 50 degrees; in particular, the motorcycle Smartphones and smartphones are very convenient tools. During the process of riding on the road, when a person visually sees a bad road surface on the road, he can directly ride to the bad road surface and record it to obtain several metadata.
該慣性測量裝置2,如圖3及圖10所示,係裝置於該移動載具C的後端處且更包含有一後慣性測量單元21及一傳輸單元22;其中該後慣性測量單元21感測該移動載具C後端處的B-IMU值,且該傳輸單元22可以是無線或有線,而將後慣性姿態之數據則預先傳輸至該邊緣端行動裝置1作整合,所獲得的後設資料,如底下表2、表3配合圖11所示,則為其中一後設資料(metadata):
特別一提,該傳輸單元22較佳則選用藍芽(bluetooth)傳輸。 In particular, the transmission unit 22 preferably adopts Bluetooth transmission.
該整合應用程式單元3,如圖9所示,係預存並被安裝至該邊緣端行動裝置1的記憶體單元15,並由該運算處理器17呼叫執行以針對不良路面進行錄影並蒐集該數個後設資料作儲存,並同時令該通信單元16上傳到雲端伺服器4。 The integrated application unit 3, as shown in Figure 9, is pre-stored and installed in the memory unit 15 of the edge mobile device 1, and is called and executed by the computing processor 17 to record the bad road surface and collect the data. The metadata is stored, and the communication unit 16 is uploaded to the cloud server 4 at the same time.
該雲端伺服器4,係接收該邊緣端行動裝置1所傳來含MP4、GPS、F-IMU值、B-IMU值之數個後設資料,且該雲端伺服器4更包含有一路面辨識模組41,而該路面辨識模組41會依據該數個後設資料分別辨識出不良路面的PCI鋪面狀況指標的特徵值並儲存之,並最終辨識結果會提供藉由該GPS的位置資訊輸出顯示於一地理資訊系統上。 The cloud server 4 receives several metadata including MP4, GPS, F-IMU values, and B-IMU values from the edge mobile device 1, and the cloud server 4 further includes a road surface recognition model. Group 41, and the road surface identification module 41 will respectively identify the characteristic values of the PCI pavement condition index of the bad road surface based on the several metadata and store them, and the final identification result will provide the location information output display through the GPS. on a geographic information system.
因此,本發明提供一種交通路面智慧檢測系統及其邊緣收集裝置之較佳解決方案,待把該邊緣端行動裝置1裝好於該移動載具C並啟動後,執行該整合應用程式單元3,便會開啟該邊緣端行動裝置1的辨識功能,且同時校正該鏡頭單元11的拍攝角度θ後,呼叫該邊緣端行動裝置1中GPS、F-IMU、鏡頭單元11及該慣性測量裝置2的B-IMU;然後載入Tensorflow函式庫並向雲端伺服器4呼叫路面標記檔後,開始運用Tensorflow初步辨識PCI鋪面特徵,當辨識到裂縫、坑洞等時,開始記錄GPS、F-IMU、B-IMU及MP4之後設資料;最後啟動背景傳輸,如果有網路則傳輸所記錄的後設資料到雲端伺服器4作進一步作詳細辨識PCI鋪面特徵, 即該路面辨識模組41會根據F-IMU、B-IMU數據,如圖12所示,找出特徵波形及各項九軸參數,由於不同的PCI鋪面特徵會產生,最後該路面辨識模組41會依據不同的九軸參數,進而辨識出各PCI鋪面特徵,倘若沒網路則傳輸所記錄的後設資料傳輸到本端並預先作儲存,等有網路時在上傳至雲端。 Therefore, the present invention provides a better solution for a traffic road intelligent detection system and its edge collection device. After the edge mobile device 1 is installed on the mobile vehicle C and started, the integrated application unit 3 is executed. The recognition function of the edge-end mobile device 1 will be turned on, and after correcting the shooting angle θ of the lens unit 11, the GPS, F-IMU, lens unit 11 and the inertial measurement device 2 in the edge-end mobile device 1 will be called. B-IMU; then load the Tensorflow function library and call the road marking file to the cloud server 4, and then use Tensorflow to initially identify the PCI pavement features. When cracks, potholes, etc. are identified, start recording the GPS, F-IMU, B-IMU and MP4 post-configuration data; finally start background transmission, and if there is a network, transmit the recorded meta-data to the cloud server 4 for further detailed identification of PCI pavement characteristics. That is, the road surface identification module 41 will find the characteristic waveform and various nine-axis parameters based on the F-IMU and B-IMU data as shown in Figure 12. Since different PCI pavement characteristics will be generated, the road surface identification module will finally 41 will identify the characteristics of each PCI floor based on different nine-axis parameters. If there is no network, the recorded metadata will be transmitted to the local end and stored in advance, and then uploaded to the cloud when there is a network.
提供用於前述交通路面智慧檢測方法的一種邊緣收集裝置,則其僅包含有:前述該邊緣端行動裝置1、前述該慣性測量裝置2及前述該整合應用程式單元3等,而該邊緣收集裝置則專門以蒐集不良鋪面的MP4、GPS、F-IMU值、B-IMU值等之數個後設資料,並上傳至雲端伺服器4以進行後續處理。特別一提,如圖13所示,本發明進行資訊蒐集時,由於隨時有GPS、智慧型手機的F-IMU、B-IMU、影像等相關數據資料進入,此為大數據型之數據來源,即本發明可利用大數據技術來進行資料處理,換言之,當從某設備(資料來源),發現有狀況發生(問題特徵),定義為某狀況事件,並通知相關人員進行處理(腳本式回應),據以提升設備問題等之解決效率。 Provide an edge collection device for the aforementioned intelligent detection method of traffic road surface, which only includes: the aforementioned edge-side mobile device 1, the aforementioned inertial measurement device 2, the aforementioned integrated application unit 3, etc., and the edge collection device It is specifically designed to collect several metadata such as MP4, GPS, F-IMU value, B-IMU value, etc. of defective pavements, and upload them to the cloud server 4 for subsequent processing. In particular, as shown in Figure 13, when the present invention collects information, since relevant data such as GPS, F-IMU, B-IMU, and images of smartphones enter at any time, this is a big data source. That is, the present invention can use big data technology for data processing. In other words, when a situation occurs (problem characteristics) from a certain device (data source), it is defined as a certain situation event, and relevant personnel are notified for processing (scripted response) , to improve the efficiency of solving equipment problems.
B:交通路面智慧檢測系統 B: Traffic road intelligent detection system
C:移動載具 C:Mobile vehicle
C1:手機架 C1: mobile phone holder
1:邊緣端行動裝置 1: Edge mobile devices
2:慣性測量裝置 2: Inertial measurement device
3:整合應用程式單元 3: Integrate application units
4:雲端伺服器 4:Cloud server
41:路面辨識模組 41: Pavement recognition module
5:地理資訊系統 5:Geographic information system
Claims (8)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111150396A TWI821089B (en) | 2022-12-28 | 2022-12-28 | Traffic road intelligent detection system and edge collection device |
US18/181,304 US20240221393A1 (en) | 2022-12-28 | 2023-03-09 | Smart road surface detection method and edge collection device, cloud-based road surface recognition module and system thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111150396A TWI821089B (en) | 2022-12-28 | 2022-12-28 | Traffic road intelligent detection system and edge collection device |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI821089B true TWI821089B (en) | 2023-11-01 |
TW202426731A TW202426731A (en) | 2024-07-01 |
Family
ID=89722215
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111150396A TWI821089B (en) | 2022-12-28 | 2022-12-28 | Traffic road intelligent detection system and edge collection device |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI821089B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW202024995A (en) * | 2018-12-21 | 2020-07-01 | 億增營造有限公司 | Intelligent road defects identification method and system thereof wherein the intelligent road defects identification system includes a traveling vehicle image capturing device, a road analysis module, and a road defects identification module |
CN111648214A (en) * | 2020-06-01 | 2020-09-11 | 中公诚科(吉林)工程检测有限公司 | Pavement state comprehensive detection system based on CCD and laser signal source combined measurement |
CN111754766A (en) * | 2019-03-29 | 2020-10-09 | 本田技研工业株式会社 | Information acquisition device |
CN114729513A (en) * | 2019-11-15 | 2022-07-08 | 倍耐力轮胎股份公司 | Method and system for evaluating unevenness parameters of a road section |
-
2022
- 2022-12-28 TW TW111150396A patent/TWI821089B/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW202024995A (en) * | 2018-12-21 | 2020-07-01 | 億增營造有限公司 | Intelligent road defects identification method and system thereof wherein the intelligent road defects identification system includes a traveling vehicle image capturing device, a road analysis module, and a road defects identification module |
CN111754766A (en) * | 2019-03-29 | 2020-10-09 | 本田技研工业株式会社 | Information acquisition device |
CN114729513A (en) * | 2019-11-15 | 2022-07-08 | 倍耐力轮胎股份公司 | Method and system for evaluating unevenness parameters of a road section |
CN111648214A (en) * | 2020-06-01 | 2020-09-11 | 中公诚科(吉林)工程检测有限公司 | Pavement state comprehensive detection system based on CCD and laser signal source combined measurement |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109870456B (en) | Rapid detection system and method for road surface health condition | |
CN109165582B (en) | Urban street garbage detection and cleanliness assessment method | |
Hadjidemetriou et al. | Automated pavement patch detection and quantification using support vector machines | |
CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
CN112800913B (en) | Pavement damage data space-time analysis method based on multi-source feature fusion | |
CN112800911B (en) | Pavement damage rapid detection and natural data set construction method | |
CN106296814B (en) | Highway maintenance detection and virtual interactive interface method and system | |
CN111458721B (en) | Exposed garbage identification and positioning method, device and system | |
Wang et al. | Traffic sensory data classification by quantifying scenario complexity | |
CN108107462A (en) | The traffic sign bar gesture monitoring device and method that RTK is combined with high speed camera | |
Benmhahe et al. | Automated pavement distress detection, classification and measurement: A review | |
CN114971166A (en) | Lightweight road pavement service quality inspection system | |
KR102562757B1 (en) | Prediction and recognition method of road marking information and road maintenance method | |
Alshammari et al. | 3Pod: Federated Learning-based 3 Dimensional Pothole Detection for Smart Transportation | |
JP2022003548A (en) | Recognition system and program for the same | |
CN111723643B (en) | Target detection method based on fixed-area periodic image acquisition | |
TWI821089B (en) | Traffic road intelligent detection system and edge collection device | |
TWI828495B (en) | Traffic road intelligent detection method and cloud road surface identification module | |
Kandoi et al. | Pothole detection using accelerometer and computer vision with automated complaint redressal | |
CN117422699A (en) | Highway detection method, highway detection device, computer equipment and storage medium | |
CN108573220B (en) | Road crack identification method based on group multi-source data | |
Li et al. | Road Damage Evaluation via Stereo Camera and Deep Learning Neural Network | |
Dhoundiyal et al. | Deep Learning Framework for Automated Pothole Detection | |
US20240221393A1 (en) | Smart road surface detection method and edge collection device, cloud-based road surface recognition module and system thereof | |
Sun et al. | UAV photogrammetry-based accident assessment road condition analysis using image classification |