CN105491327A - Video tracking method and device based on road network - Google Patents
Video tracking method and device based on road network Download PDFInfo
- Publication number
- CN105491327A CN105491327A CN201510793902.XA CN201510793902A CN105491327A CN 105491327 A CN105491327 A CN 105491327A CN 201510793902 A CN201510793902 A CN 201510793902A CN 105491327 A CN105491327 A CN 105491327A
- Authority
- CN
- China
- Prior art keywords
- node
- road
- path
- headend equipment
- joined
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a video tracking method and device based on a road network. The video tracking method comprises the following steps: analyzing a suspicious node and a path of a suspected target from a crime scene to a set radius based on the road network; finding out video monitoring front-end equipment on the suspicious node and the path; and on the basis of a searched path, performing priority ranking on all found front-end equipment according a visible range of the front-end equipment and a distance between the front-end equipment and a starting point, checking videos of the front-end equipment according to the ranking and tracking the target. The device of the invention comprises a path search module, a front-end equipment search module and a ranking tracking module. The method and device of the invention can more quickly acquire video records of the suspected target and help to more quickly uncover a case.
Description
Technical field
The invention belongs to video frequency tracking technical field, particularly relate to a kind of video frequency tracking method based on road network and device.
Background technology
Video monitoring is the important component part of safety and protection system, and video monitoring is directly perceived with it, accurately, timely and the information content is abundant and be widely used in many occasions.In recent years, along with the develop rapidly of computer, network and image procossing, transmission technology, the universalness trend of video monitoring is more and more obvious.The effect that video monitoring plays in the security protection of city is increasing, the public security of generation, break in traffic rules and regulations and criminal case, much all relies on the video image of the CCTV camera record of distribution in city to obtain final detection.
But in the prior art, if there is events such as pilferage cases, need to investigate and suspicion is followed the trail of monitor video video recording, often need to investigate one by one according to the time period the video record of the video camera around venue location point at that time, find out the video photographing suspected target, to carry out further investigation and evidence obtaining, these needs of work are manually cruised to appointed area by the staff of relevant departments and check.But often need when checking to specify the span larger time period to carry out playback, in order to avoid miss the picture of suspected target appearance, this investigates one by one with regard to needing a large amount of time and efforts of cost investigation personnel in charge of the case, the probability of the error and omission followed the trail of is very large, and this is that during the serious criminal cases such as similar pilferage are investigated, institute is unallowed.Therefore how being screened by those video cameras that may photograph suspected target fast, improve the efficiency of investigating and collecting evidence, is the problem that video monitoring system urgently needs to solve.
Prior art often delimit crime region centered by crime place, zone radius delimited in conjunction with actual conditions, and all video cameras found out in this crime region, check the playing back videos of all video cameras in crime region successively, playback from the crime time, see if there is suspected target to occur, if any, then record this video camera stored in list.After having checked all video cameras, the list of gained is all video cameras of suspected target process, connects these video cameras, the path formed namely think suspected target the track of process.It is lower that the shortcoming of this technical scheme is mainly reflected in search efficiency, because current the time point knowing crime, and the video camera in crime region is not carried out selecting or sorting, so when checking all video cameras in crime region successively, need from crime time point, check video recording always backward, this is by the time of at substantial and workload, and check in video process and must keep concentrating of attentiveness the moment, because and do not know that suspected target can occur time period within which, search efficiency can be had a greatly reduced quality
Summary of the invention
The object of this invention is to provide a kind of video frequency tracking method based on road network and device, checking successively in order to avoid prior art needs all video cameras in crime region to search from crime time point, the technical problem that efficiency is lower.
To achieve these goals, technical solution of the present invention is as follows:
Based on a video frequency tracking method for road network, described method comprises:
In road network, determine that the point on the road that distance venue location is nearest is starting point, search out the suspect node in the scope radius D of setting and path;
Find out the video monitoring front end equipment on suspect node and path;
In the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, checks that the video recording of headend equipment realizes the tracking to target according to sequence.
Further, described in the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, comprising:
In the path basis searched out, for headend equipment arranges ranking factor, described ranking factor is the total road number in road number/this headend equipment location crossing with headend equipment visible range;
Headend equipment is divided at least two regions by the distance according to headend equipment distance starting point, sorts respectively, finally sorted by all region merging technique to the headend equipment of regional according to ranking factor.
Further, describedly in road network, determine that the point on the nearest road of distance venue location is starting point, search out the suspect node in the scope radius D of setting and path, comprise
Step 1, initialization, arrange set B, set R and dictionary T for empty, according to the latitude and longitude information of the venue location of input, determines that the point on the road that distance venue location is nearest is starting point in road network;
Step 2, in road network, check the road at this starting point place, whether be one-way road according to this road, the terminal node of road is joined in set B, or the start node of road and terminal node are all joined in set B, and for the node joined in set B, the respective paths between itself and starting point is joined in dictionary T;
Step 3, in set B, to search in set B node not in set R, if do not found, terminate and return results set R and dictionary T, if found, the node according to finding searches the shortest path of distance corresponding to these nodes in dictionary T, judge whether this path is less than the scope radius D of setting, if then node corresponding for this path to be joined set R, and from set B, delete the node that this path is corresponding, otherwise do not add, in set B, delete this node and return set R and dictionary T;
Step 4, for the node P newly joined in set R, look in road network and see if there is node and communicate with this node P, if, do not return step 3, if there is the node communicated with this node P, then check whether this node communicated is included in dictionary T, if be included in dictionary T, then the path being arrived the node that this communicates by node P is joined in dictionary T, and judge whether the number in the path arriving this node communicated is greater than the threshold k of setting, if be greater than, deleted after arriving this node middle distance communicated path farthest in dictionary T and return step 3, if this node communicated is not included in dictionary T, then the node that this communicates is joined in set B, and the path being arrived the node that this communicates by node P is joined after in dictionary T return step 3,
Wherein, described set B is the set of the still undetermined node of shortest path, and set R is the set of the node that shortest path has been determined, dictionary T is the path collection found.
Further, whether described be one-way road according to this road, joined in set B by the terminal node of road, or the start node of road and terminal node are all joined in set B, comprising:
Judge whether this road is one-way road;
If this road is one-way road, then the terminal node of road is joined in set B;
If this road is two ways, then the start node of road and terminal node are all joined in set B.
Further, the described tracking of video recording realization to target checking headend equipment according to sequence, also comprises:
According to starting point to each paths of headend equipment place node and the prior average translational speed V of target set, calculate each time point that target arrives this headend equipment, when the video recording checking this headend equipment, check from the time point calculated respectively.
The invention allows for a kind of video frequency tracking device based on road network, described device comprises:
Path searcher module, for determining that in road network the point on the road that distance venue location is nearest is starting point, searches out the suspect node in the scope radius D of setting and path;
Headend equipment searches module, for finding out the video monitoring front end equipment on suspect node and path;
Sequence tracing module, for the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, checks that the video recording of headend equipment realizes the tracking to target according to sequence.
Further, when described sequence tracing module checks that the video recording of headend equipment realizes the tracking to target according to sequence, also for according to the target average translational speed V of starting point to each paths of headend equipment place node and in advance setting, calculate each time point that target arrives this headend equipment, when the video recording checking this headend equipment, check from the time point calculated respectively.
A kind of video frequency tracking method based on road network that the present invention proposes and device, suspected target is analyzed from spot to the suspect path in the scope radius set based on road network, significance level sequence is carried out to the video camera in scope, and obtain several material time points that object arrives each video camera, more record a video deposit card to obtain suspected target, help to obtain part of solving a case faster.
Accompanying drawing explanation
Fig. 1 is the video frequency tracking method flow diagram that the present invention is based on road network;
Fig. 2 is embodiment of the present invention road network schematic diagram;
Fig. 3 is the node that finds of the embodiment of the present invention and path schematic diagram.
Embodiment
Be described in further details technical solution of the present invention below in conjunction with drawings and Examples, following examples do not form limitation of the invention.
General thought of the present invention take venue location as starting point, goes out many shortest paths in setting range radius D based on road network search, according to node and the path of all processes obtained, finds out the headend equipment on these paths, and carry out video and check.The headend equipment needing to carry out video and check can be found more accurately, decrease the workload that video is checked, improve operating efficiency.
As shown in Figure 1, a kind of video frequency tracking method based on road network of the present embodiment, comprising:
Step S1, in road network, determine that the point on the nearest road of distance venue location is starting point, search out the suspect node in the scope radius D of setting and path;
Step S2, the video monitoring front end equipment found out on suspect node and path;
Step S3, in the path basis searched out, according to the distance of the visible range of headend equipment and headend equipment distance starting point, prioritization is carried out to all headend equipments found out, checks that the video recording of headend equipment realizes the tracking to target according to sequence.
Wherein, go out the suspect node in the scope radius D of setting and path based on road network search, refer to the track that suspected target may be advanced in specified scope radius D.The many factors such as the vehicles, weather, time that suspect node and path can be taken according to the character of event, target, the node of the target process in artificial selected road network in scope radius D and path.But the impact of the artificial subjective analysis of this method is large, not comprehensively.
Preferably, step S1 search procedure comprises the steps:
Step S1.1, initialization, arrange set B, set R and dictionary T for empty, according to the latitude and longitude information of the venue location of input, determines that the point on the road that distance venue location is nearest is starting point in road network.
Road network is made up of road and node, and be stored as V in a database and show and E table, memory node information in V table, mainly comprises node coordinate and numbering, and E table stores road information, mainly stores the path of road, the starting point of road and terminal.Objective world cannot be covered completely owing to using road and node in road network, road network is thought except the topological road described in roadnet, what there are not other can pass, and longitude and latitude is the coordinate system of an all standing, so need the latitude and longitude information of venue location to be corresponded to the node in road network or the point on road.
The present embodiment for crime for venue location, in the application of reality, venue location can also be spot of focus incident etc., first by the latitude and longitude information on crime ground, project in road network, calculate the road that distance crime ground is nearest, afterwards calculating the point that on this road, distance crime ground is nearest, using this nearest point as starting point.
In the present embodiment, set B is the set of the still undetermined node of shortest path, and set R is the set of the node that shortest path has been determined, dictionary T is the path collection found.
Step S1.2, in road network, check the road at this starting point place, whether be one-way road according to this road, the terminal node of road is joined in set B, or the start node of road and terminal node are all joined in set B, and for the node joined in set B, the respective paths between itself and starting point is joined in dictionary T.
As shown in Figure 2, after finding starting point according to step S1.1, in road network, determine the road at starting point place, and the start node of this road and terminal node.If this road is one-way road, if criminal drives to leave and follows traffic rules (if do not follow traffic rules, all roads are all two ways, if do not driven, all roads are all two ways), so he first can only arrive terminal node, so terminal node is joined in set B, and path is joined in set T.If this road is two ways, then the start node of road and terminal node are all joined in set B, and path is joined in set T.No matter visible be one-way road or two ways, for the node joined in set B, the respective paths between itself and starting point joined in dictionary T.
Suppose that the road at starting point place is one way access, the terminal node of this road be numbered x
1, so set B just includes this numbering x
1, wherein set B is the set of the still undetermined node of shortest path.Dictionary T is the path collection found, node x
1after joining set B, starting point is to node x
1path be added into set T.
The road supposing starting point place for being not one way access, the terminal node of this road be numbered x
1, start node be numbered x
2, so set B just includes this numbering x
1and x
2, wherein set B is the set of the still undetermined node of shortest path.Dictionary T is the path collection found, node x
1and x
2after joining set B, starting point is to node x
1path, starting point is to node x
2path be added into set T.
Although the road due to starting point place is one-way road, but criminal does not likely observe traffic rules and regulations, or criminal does not leave by bus, whether therefore before determining that the start node of this road and terminal node which this join in set B, also needing this road is that one-way road is determined.Namely whether the present embodiment is being one-way road according to this road, joined in set B by the terminal node of road, or before all joining in set B by the start node of road and terminal node, also comprises step:
Whether the road determining starting point place is one-way road.
Thus could determine when being one-way road, the terminal node of road is joined in set B, when two ways, the start node of road and terminal node is all joined in set B.
Step S1.3, in set B, to search in set B node not in set R, if do not found, terminate and return results set R and dictionary T, if found, the node according to finding searches the shortest path of distance corresponding to these nodes in dictionary T, judge whether this path is less than the scope radius D of setting, if then node corresponding for this path to be joined set R, and from set B, delete the node that this path is corresponding, otherwise do not add, in set B, delete this node and return set R and dictionary T.
Circulation time for the first time, set B only has 1 or two nodes, if one-way road is exactly a terminal node x
1if two ways are exactly start node x
2with terminal node x
1.Find wherein with start point distance from that shorter node, this node is joined in set R, and in set B, removes this node.Suppose terminal node x
1path distance to starting point is short, then by terminal node x
1join set R, and from set B, delete terminal node x
1.Visible by step S1.3, start node x can be found
2with terminal node x
1the node that middle distance starting point is nearest, is assumed to be x
1, then by x
1delete from set B, retain x
2.
If the shortest path of distance corresponding to node in set B not in set R is greater than the scope radius D of setting, then from conjunction with deleting this node B, poll-final also returns results set R and dictionary T, and all paths in expression scope radius D have all been found out and path is stored in dictionary T.
It should be noted that, if search the node not in set R in set B in set B, when the shortest path of the distance that the node found is corresponding is all greater than the scope radius D of setting, these nodes all can be deleted from set B, then can not also directly terminate, but enter next step, do not need to perform at next step S1.4 and directly return step S1.3 (because newly not adding the point in conjunction with R), and step S1.3 searches the node in set B not in set R in set B, then do not find any node, can terminate and return results set R and dictionary T, all paths in expression scope radius D have all been found out and path is stored in T, here repeat no more.
Step S1.4, for the node P newly joined in set R, look in road network and see if there is node and communicate with this node P, if, do not return step S1.3, if there is the node communicated with this node P, then check whether this node communicated is included in dictionary T, if be included in dictionary T, then the path being arrived the node that this communicates by node P is joined in dictionary T, and judge whether the number in the path arriving this node communicated is greater than the threshold k of setting, if be greater than, deleted after arriving this node middle distance communicated path farthest in dictionary T and return step S1.3, if this node communicated is not included in dictionary T, then the node that this communicates is joined in set B, and the path being arrived the node that this communicates by node P is joined after in dictionary T return step S1.3.
Then for the node x newly joined in set R
1, look in road network and see if there is node and this node x
1communicate, if not, return step S1.3 and circulate next time.
If had and this node x
1the node communicated, is assumed to be x
3, then this node x communicated is checked
3whether be included in dictionary T, if be included in dictionary T, then will by node x
1arrive the node x that this communicates
3path join in dictionary T, and judge arrive this node x communicated
3the number in path whether be greater than the threshold k of setting, if be greater than, deleted in dictionary T and arrive this node x communicated
3middle distance path farthest, if this node x communicated
3be not included in dictionary T, then the node x this communicated
3join in set B, and will by node x
1arrive the node x that this communicates
3path join in dictionary T.
The threshold k wherein set is the number of passes that this node communicated arrives starting point, generally can be arranged on 2 or 3, user generally needs to find the shortest, secondary short and again short road strength, more path is just nonsensical, and the setting of K value searches the number of passes of a node to starting point to limit.
Thus gradually according to the node P newly joined in set R, extend, the node communicated with P is joined in set B, and return step S1.3 and carry out cycle criterion, in specified scope radius D, find out rapidly the track that all criminals may advance.
By node x
3join after in set B, in set B, there is x
3and x
2, turn back to step S1.3, find wherein with start point distance from that shorter node, this node is joined in set R, and in set B, removes this node.
Suppose second time circulation time, x
2with start point distance from shorter, then by x
2join set R, and proceed to step S1.4 and check and x
2the node communicated, the like, expand to the periphery gradually, terminate after finding all shortest paths in the scope radius D of setting.
Fig. 3 shows the node and path schematic diagram that the present embodiment finds, through step S1.1-S1.4, get in scope radius D all set R in node and path after, general near nodal is all provided with headend equipment web camera IPC, hypothetical target is all the section of target likely process from O, OA, OB, OC, OD, AK, AE, BF, BG, CH etc.Below with Fig. 3 in order to elaborate how in the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, checks that the video recording of headend equipment realizes the tracking to target according to sequence:
Step S3.1, in the path basis searched out, for headend equipment arranges ranking factor, described ranking factor is the total road number in road number/this headend equipment location crossing with headend equipment visible range.
Headend equipment priority in Fig. 3 near crossing A, B, C, D is just relatively the highest, its circle formed is nearest from crime ground, and the headend equipment priority near crossing E, F, G, H, I, J, K will be lower than A, B, C, D because its formed circle from crime ground distance relatively away from.It is easily understood that from crime place more close to node, the probability of target process is just relatively larger, therefore the present embodiment carries out prioritization to headend equipment from inside to outside with the form of circle, checks the video recording of headend equipment according to the sequence of priority, searching clue.
Particularly, headend equipment all has visible range, if target is through OA section, so can affirm that target will appear in headend equipment A, because the visible range of headend equipment A covers section AE, AK; If target is through OB section or OD section, so object likely appears in headend equipment B or D; And if target is through OC section, then it there will not be certainly in headend equipment C, because the visible range of headend equipment C does not cover any section.Thus, ranking factor λ can be extracted:
Wherein, n is the section number that the visible range of headend equipment therewith intersects, and N is with the total road number in this headend equipment location.
Step S3.2, according to headend equipment distance starting point distance headend equipment is divided at least two regions, respectively the headend equipment of regional is sorted according to ranking factor, finally all region merging technique is sorted.
Headend equipment in gamut radius D is divided into inner ring and outer ring according to the distance of headend equipment distance venue location by the present embodiment, inner ring comprises A, B, C, D, and outer ring comprises E, F, G, H, I, J, K, first the headend equipment of inner ring is sorted according to ranking factor λ, then the headend equipment of inner ring is sorted according to ranking factor λ, finally ordering by merging is carried out to the headend equipment of inner ring and outer ring.
Such as: set two set M and N, M represents the set of the high headend equipment of priority, and N represents the set of the lower headend equipment of priority, and M is used for depositing the headend equipment that λ is greater than 0, N is used for depositing the headend equipment of λ=0, then carry out following arrangement to the headend equipment of inner ring:
| Set M |
| A |
| B |
| D |
Table 1
| Set N |
| C |
Table 2
By that analogy, can sort to the headend equipment of outer ring, and upgrade set M and N.Such as, when sorting to the headend equipment of outer ring, will upgrade set M and N on inner ring ranking results basis, its result is as follows:
| Set M |
| A |
| B |
| D |
| J |
| E |
| G |
| H |
| I |
Table 3
| Set N |
| C |
| F |
| K |
Table 4
Finally ordering by merging is carried out to the headend equipment of inner ring and outer ring, just obtains the final sequence of headend equipment as following table:
| Headend equipment |
| M |
| N |
Table 5
It should be noted that, the present embodiment lists inner ring and outer ring, and inner ring and outer ring are also divide according to the distance of headend equipment distance starting point, also can be divided into more circle, such as three circles or four circles, but the principle of sequence are similar, repeats no more here.
Then after the sequence completing headend equipment, first can check the headend equipment that priority is high, the video recording more easily full out finding target to occur.In order to save the time of searching further, the method for the present embodiment also comprises step:
According to starting point to each paths of headend equipment place node and the prior average translational speed V of target set, calculate each time point that target arrives this headend equipment, when the video recording checking this headend equipment, check from the time point calculated respectively.
Particularly, according to the target average translational speed V of starting point to the K bar shortest path of present node and in advance setting, calculate target and arrive K time period (T required for this headend equipment
1~ T
k).Thus, no longer need from crime time ST when checking headend equipment video recording, and can from ST+T
i(i=1,2 ... K) start to check, pay close attention to the video recording near these time points, effectively reduce the time of searching.
With said method accordingly, a kind of video frequency tracking device based on road network of the present embodiment, comprising:
Path searcher module, for determining that in road network the point on the road that distance venue location is nearest is starting point, searches out the suspect node in the scope radius D of setting and path;
Headend equipment searches module, for finding out the video monitoring front end equipment on suspect node and path;
Sequence tracing module, for the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, checks that the video recording of headend equipment realizes the tracking to target according to sequence.
Wherein, sequence tracing module, in the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, is carried out prioritization to all headend equipments found out, is performed and operate as follows:
In the path basis searched out, for headend equipment arranges ranking factor, described ranking factor is the total road number in road number/this headend equipment location crossing with headend equipment visible range;
Headend equipment is divided at least two regions by the distance according to headend equipment distance starting point, sorts respectively, finally sorted by all region merging technique to the headend equipment of regional according to ranking factor.
Wherein, path searcher module determines that in road network the point on the road that distance venue location is nearest is starting point, searches out the suspect node in the scope radius D of setting and path, performs and operate as follows:
Initialization, arranges set B, set R and dictionary T for empty, according to the latitude and longitude information of the venue location of input, determines that the point on the road that distance venue location is nearest is starting point in road network;
The road at this starting point place is checked in road network, whether be one-way road according to this road, the terminal node of road is joined in set B, or the start node of road and terminal node are all joined in set B, and for the node joined in set B, the respective paths between itself and starting point is joined in dictionary T;
The node not in set R in set B is searched in set B, if do not found, terminate and return results set R and dictionary T, if found, the node according to finding searches the shortest path of distance corresponding to these nodes in dictionary T, judge whether this path is less than the scope radius D of setting, if then node corresponding for this path to be joined set R, and from set B, delete the node that this path is corresponding, otherwise do not add, in set B, delete this node and return set R and dictionary T;
For the node P newly joined in set R, look in road network and see if there is node and communicate with this node P, if, do not return previous step, if there is the node communicated with this node P, then check whether this node communicated is included in dictionary T, if be included in dictionary T, then the path being arrived the node that this communicates by node P is joined in dictionary T, and judge whether the number in the path arriving this node communicated is greater than the threshold k of setting, if be greater than, deleted after arriving this node middle distance communicated path farthest in dictionary T and return previous step, if this node communicated is not included in dictionary T, then the node that this communicates is joined in set B, and the path being arrived the node that this communicates by node P is joined after in dictionary T return previous step,
Wherein, described set B is the set of the still undetermined node of shortest path, and set R is the set of the node that shortest path has been determined, dictionary T is the path collection found.
Wherein, whether path searcher module, being one-way road according to this road, joins the terminal node of road in set B, or when the start node of road and terminal node all being joined in set B, performs and operate as follows:
Judge whether this road is one-way road;
If this road is one-way road, then the terminal node of road is joined in set B;
If this road is two ways, then the start node of road and terminal node are all joined in set B.
Further, when sequence tracing module checks that the video recording of headend equipment realizes the tracking to target according to sequence, also for according to the target average translational speed V of starting point to each paths of headend equipment place node and in advance setting, calculate each time point that target arrives this headend equipment, when the video recording checking this headend equipment, check from the time point calculated respectively.
Above embodiment is only in order to illustrate technical scheme of the present invention but not to be limited; when not deviating from the present invention's spirit and essence thereof; those of ordinary skill in the art are when making various corresponding change and distortion according to the present invention, but these change accordingly and are out of shape the protection range that all should belong to the claim appended by the present invention.
Claims (10)
1. based on a video frequency tracking method for road network, it is characterized in that, described method comprises:
In road network, determine that the point on the road that distance venue location is nearest is starting point, search out the suspect node in the scope radius D of setting and path;
Find out the video monitoring front end equipment on suspect node and path;
In the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, checks that the video recording of headend equipment realizes the tracking to target according to sequence.
2. the video frequency tracking method based on road network according to claim 1, it is characterized in that, described in the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, comprising:
In the path basis searched out, for headend equipment arranges ranking factor, described ranking factor is the total road number in road number/this headend equipment location crossing with headend equipment visible range;
Headend equipment is divided at least two regions by the distance according to headend equipment distance starting point, sorts respectively, finally sorted by all region merging technique to the headend equipment of regional according to ranking factor.
3. the video frequency tracking method based on road network according to claim 1, is characterized in that, describedly in road network, determines that the point on the nearest road of distance venue location is starting point, searches out the suspect node in the scope radius D of setting and path, comprises
Step 1, initialization, arrange set B, set R and dictionary T for empty, according to the latitude and longitude information of the venue location of input, determines that the point on the road that distance venue location is nearest is starting point in road network;
Step 2, in road network, check the road at this starting point place, whether be one-way road according to this road, the terminal node of road is joined in set B, or the start node of road and terminal node are all joined in set B, and for the node joined in set B, the respective paths between itself and starting point is joined in dictionary T;
Step 3, in set B, to search in set B node not in set R, if do not found, terminate and return results set R and dictionary T, if found, the node according to finding searches the shortest path of distance corresponding to these nodes in dictionary T, judge whether this path is less than the scope radius D of setting, if then node corresponding for this path to be joined set R, and from set B, delete the node that this path is corresponding, otherwise do not add, in set B, delete this node and return set R and dictionary T;
Step 4, for the node P newly joined in set R, look in road network and see if there is node and communicate with this node P, if, do not return step 3, if there is the node communicated with this node P, then check whether this node communicated is included in dictionary T, if be included in dictionary T, then the path being arrived the node that this communicates by node P is joined in dictionary T, and judge whether the number in the path arriving this node communicated is greater than the threshold k of setting, if be greater than, deleted after arriving this node middle distance communicated path farthest in dictionary T and return step 3, if this node communicated is not included in dictionary T, then the node that this communicates is joined in set B, and the path being arrived the node that this communicates by node P is joined after in dictionary T return step 3,
Wherein, described set B is the set of the still undetermined node of shortest path, and set R is the set of the node that shortest path has been determined, dictionary T is the path collection found.
4. the video frequency tracking method based on road network according to claim 3, it is characterized in that, whether described be one-way road according to this road, joins in set B by the terminal node of road, or the start node of road and terminal node are all joined in set B, comprising:
Judge whether this road is one-way road;
If this road is one-way road, then the terminal node of road is joined in set B;
If this road is two ways, then the start node of road and terminal node are all joined in set B.
5. the video frequency tracking method based on road network according to claim 1, is characterized in that, the described tracking of video recording realization to target checking headend equipment according to sequence, also comprises:
According to starting point to each paths of headend equipment place node and the prior average translational speed V of target set, calculate each time point that target arrives this headend equipment, when the video recording checking this headend equipment, check from the time point calculated respectively.
6. based on a video frequency tracking device for road network, it is characterized in that, described device comprises:
Path searcher module, for determining that in road network the point on the road that distance venue location is nearest is starting point, searches out the suspect node in the scope radius D of setting and path;
Headend equipment searches module, for finding out the video monitoring front end equipment on suspect node and path;
Sequence tracing module, for the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, checks that the video recording of headend equipment realizes the tracking to target according to sequence.
7. the video frequency tracking device based on road network according to claim 6, it is characterized in that, described sequence tracing module is in the path basis searched out, according to the visible range of headend equipment and the distance of headend equipment distance starting point, prioritization is carried out to all headend equipments found out, performs and operate as follows:
In the path basis searched out, for headend equipment arranges ranking factor, described ranking factor is the total road number in road number/this headend equipment location crossing with headend equipment visible range;
Headend equipment is divided at least two regions by the distance according to headend equipment distance starting point, sorts respectively, finally sorted by all region merging technique to the headend equipment of regional according to ranking factor.
8. the video frequency tracking device based on road network according to claim 6, it is characterized in that, described path searcher module determines that in road network the point on the road that distance venue location is nearest is starting point, searches out the suspect node in the scope radius D of setting and path, performs and operate as follows:
Initialization, arranges set B, set R and dictionary T for empty, according to the latitude and longitude information of the venue location of input, determines that the point on the road that distance venue location is nearest is starting point in road network;
The road at this starting point place is checked in road network, whether be one-way road according to this road, the terminal node of road is joined in set B, or the start node of road and terminal node are all joined in set B, and for the node joined in set B, the respective paths between itself and starting point is joined in dictionary T;
The node not in set R in set B is searched in set B, if do not found, terminate and return results set R and dictionary T, if found, the node according to finding searches the shortest path of distance corresponding to these nodes in dictionary T, judge whether this path is less than the scope radius D of setting, if then node corresponding for this path to be joined set R, and from set B, delete the node that this path is corresponding, otherwise do not add, in set B, delete this node and return set R and dictionary T;
For the node P newly joined in set R, look in road network and see if there is node and communicate with this node P, if, do not return previous step, if there is the node communicated with this node P, then check whether this node communicated is included in dictionary T, if be included in dictionary T, then the path being arrived the node that this communicates by node P is joined in dictionary T, and judge whether the number in the path arriving this node communicated is greater than the threshold k of setting, if be greater than, deleted after arriving this node middle distance communicated path farthest in dictionary T and return previous step, if this node communicated is not included in dictionary T, then the node that this communicates is joined in set B, and the path being arrived the node that this communicates by node P is joined after in dictionary T return previous step,
Wherein, described set B is the set of the still undetermined node of shortest path, and set R is the set of the node that shortest path has been determined, dictionary T is the path collection found.
9. the video frequency tracking device based on road network according to claim 8, it is characterized in that, whether described path searcher module is being one-way road according to this road, the terminal node of road is joined in set B, or when the start node of road and terminal node are all joined in set B, perform and operate as follows:
Judge whether this road is one-way road;
If this road is one-way road, then the terminal node of road is joined in set B;
If this road is two ways, then the start node of road and terminal node are all joined in set B.
10. the video frequency tracking device based on road network according to claim 6, it is characterized in that, when described sequence tracing module checks that the video recording of headend equipment realizes the tracking to target according to sequence, also for according to the target average translational speed V of starting point to each paths of headend equipment place node and in advance setting, calculate each time point that target arrives this headend equipment, when the video recording checking this headend equipment, check from the time point calculated respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510793902.XA CN105491327B (en) | 2015-11-18 | 2015-11-18 | A kind of video frequency tracking method and device based on road network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510793902.XA CN105491327B (en) | 2015-11-18 | 2015-11-18 | A kind of video frequency tracking method and device based on road network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105491327A true CN105491327A (en) | 2016-04-13 |
| CN105491327B CN105491327B (en) | 2018-12-07 |
Family
ID=55678004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510793902.XA Active CN105491327B (en) | 2015-11-18 | 2015-11-18 | A kind of video frequency tracking method and device based on road network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105491327B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570147A (en) * | 2016-10-27 | 2017-04-19 | 武汉烽火众智数字技术有限责任公司 | GIS road network analysis-based jump type video tracking method and system |
| CN108174147A (en) * | 2017-12-12 | 2018-06-15 | 山东科技大学 | Video source and the Automatic Optimal distribution method of Scout service device in video monitoring system |
| CN109344290A (en) * | 2018-11-19 | 2019-02-15 | 福建工程学院 | A method of lost children is found based on block chain technology |
| CN110708509A (en) * | 2019-10-10 | 2020-01-17 | 桂林理工大学 | Eye-of-the-sky network video monitoring method for suspect tracking and feature rapid extraction |
| CN111107319A (en) * | 2019-12-25 | 2020-05-05 | 眸芯科技（上海）有限公司 | Target tracking method, device and system based on regional camera |
| CN111133748A (en) * | 2017-09-26 | 2020-05-08 | Jvc建伍株式会社 | Terminal device, camera system, and control method |
| CN112488068A (en) * | 2020-12-21 | 2021-03-12 | 重庆紫光华山智安科技有限公司 | Method, device and equipment for searching monitoring target and computer storage medium |
| CN112750301A (en) * | 2019-10-30 | 2021-05-04 | 杭州海康威视***技术有限公司 | Target object tracking method, device, equipment and computer readable storage medium |
| CN113542671A (en) * | 2020-04-21 | 2021-10-22 | 株式会社日立制作所 | Event analysis system and event analysis method |
| CN113936353A (en) * | 2021-09-18 | 2022-01-14 | 青岛海信网络科技股份有限公司 | Moving path video polling method and device of monitoring target and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102638675A (en) * | 2012-04-01 | 2012-08-15 | 安科智慧城市技术（中国）有限公司 | Method and system for target tracking by using multi-view videos |
| CN102843547A (en) * | 2012-08-01 | 2012-12-26 | 安科智慧城市技术（中国）有限公司 | Intelligent tracking method and system for suspected target |
| CN104469324A (en) * | 2014-12-25 | 2015-03-25 | 浙江宇视科技有限公司 | Moving target tracking method and device based on videos |
| CN104679864A (en) * | 2015-02-28 | 2015-06-03 | 武汉烽火众智数字技术有限责任公司 | Intelligent tracking method and intelligent tracking device for suspected target based on GIS (Geographic Information System) |
-
2015
- 2015-11-18 CN CN201510793902.XA patent/CN105491327B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102638675A (en) * | 2012-04-01 | 2012-08-15 | 安科智慧城市技术（中国）有限公司 | Method and system for target tracking by using multi-view videos |
| CN102843547A (en) * | 2012-08-01 | 2012-12-26 | 安科智慧城市技术（中国）有限公司 | Intelligent tracking method and system for suspected target |
| CN104469324A (en) * | 2014-12-25 | 2015-03-25 | 浙江宇视科技有限公司 | Moving target tracking method and device based on videos |
| CN104679864A (en) * | 2015-02-28 | 2015-06-03 | 武汉烽火众智数字技术有限责任公司 | Intelligent tracking method and intelligent tracking device for suspected target based on GIS (Geographic Information System) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570147A (en) * | 2016-10-27 | 2017-04-19 | 武汉烽火众智数字技术有限责任公司 | GIS road network analysis-based jump type video tracking method and system |
| CN106570147B (en) * | 2016-10-27 | 2020-05-08 | 武汉烽火众智数字技术有限责任公司 | Skip type video tracking method and system based on GIS road network analysis |
| CN111133748A (en) * | 2017-09-26 | 2020-05-08 | Jvc建伍株式会社 | Terminal device, camera system, and control method |
| CN111133748B (en) * | 2017-09-26 | 2021-11-30 | Jvc建伍株式会社 | Terminal device, camera system, and control method |
| CN108174147A (en) * | 2017-12-12 | 2018-06-15 | 山东科技大学 | Video source and the Automatic Optimal distribution method of Scout service device in video monitoring system |
| CN108174147B (en) * | 2017-12-12 | 2020-01-03 | 山东科技大学 | Automatic optimization allocation method for video source and tracking server in video monitoring system |
| CN109344290A (en) * | 2018-11-19 | 2019-02-15 | 福建工程学院 | A method of lost children is found based on block chain technology |
| CN110708509A (en) * | 2019-10-10 | 2020-01-17 | 桂林理工大学 | Eye-of-the-sky network video monitoring method for suspect tracking and feature rapid extraction |
| CN112750301A (en) * | 2019-10-30 | 2021-05-04 | 杭州海康威视***技术有限公司 | Target object tracking method, device, equipment and computer readable storage medium |
| CN111107319B (en) * | 2019-12-25 | 2021-05-28 | 眸芯科技（上海）有限公司 | Target tracking method, device and system based on regional camera |
| CN111107319A (en) * | 2019-12-25 | 2020-05-05 | 眸芯科技（上海）有限公司 | Target tracking method, device and system based on regional camera |
| CN113542671A (en) * | 2020-04-21 | 2021-10-22 | 株式会社日立制作所 | Event analysis system and event analysis method |
| CN112488068A (en) * | 2020-12-21 | 2021-03-12 | 重庆紫光华山智安科技有限公司 | Method, device and equipment for searching monitoring target and computer storage medium |
| CN112488068B (en) * | 2020-12-21 | 2022-01-11 | 重庆紫光华山智安科技有限公司 | Method, device and equipment for searching monitoring target and computer storage medium |
| CN113936353A (en) * | 2021-09-18 | 2022-01-14 | 青岛海信网络科技股份有限公司 | Moving path video polling method and device of monitoring target and electronic equipment |
| CN113936353B (en) * | 2021-09-18 | 2024-05-24 | 青岛海信网络科技股份有限公司 | Moving path video round-robin method and device for monitoring target and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105491327B (en) | 2018-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105491327A (en) | Video tracking method and device based on road network | |
| CN104200671B (en) | A kind of virtual bayonet socket management method based on large data platform and system | |
| CN110191424B (en) | Specific suspect track generation method and apparatus | |
| CN103942811B (en) | Distributed parallel determines the method and system of characteristic target movement locus | |
| CN102819578B (en) | Suspected target analyzing system and method by video investigation | |
| CN107292240A (en) | It is a kind of that people's method and system are looked for based on face and human bioequivalence | |
| CN106856577B (en) | Video abstract generation method capable of solving multi-target collision and shielding problems | |
| CN108052882A (en) | A kind of operating method of intelligent safety defense monitoring system | |
| CN105790955A (en) | Method and system for associating MAC addresses with face information | |
| CN106570147B (en) | Skip type video tracking method and system based on GIS road network analysis | |
| CN101430828B (en) | License plate data processing method based on traffic information extraction computation | |
| CN103578277B (en) | Deck suspicion car searching method and device thereof | |
| CN109361895B (en) | Method and system for searching suspect relation personnel | |
| CN108540752B (en) | Method, device and system for identifying target object in video monitoring | |
| CN102622580A (en) | Face detection and recognition method and system | |
| CN103546726A (en) | Method for automatically discovering illegal land use | |
| CN111107319B (en) | Target tracking method, device and system based on regional camera | |
| CN110019963B (en) | Method for searching suspect relation personnel | |
| CN106571040A (en) | Suspicious vehicle confirmation method and equipment | |
| CN111767432A (en) | Method and device for searching co-occurrence object | |
| CN103279481A (en) | Intelligent Skynet intelligence image investigation system | |
| CN111026909A (en) | Method for supplementing public security investigation data set based on self-timer tremble view | |
| CN117237418A (en) | Moving object detection method and system based on deep learning | |
| Hampapur | Smart video surveillance for proactive security [in the spotlight] | |
| CN115830076B (en) | Personnel track video intelligent analysis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |