Abnormal behavior detection method and device
A behavioral and abnormal technology, applied in the field of image processing, can solve the problems of wasting detection resources, high cost of model training and maintenance, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0059] figure 1 It is a schematic diagram of an abnormal behavior detection process provided by an embodiment of the present invention, and the process includes the following steps:
[0060] S101: Input the obtained first image to be detected into the pre-trained detection model, and based on the detection model, perform convolution processing on the first image to determine a first feature map; and determine the first The location information of the detection frame of each target object in the feature map, and the location information of the detection frame of each abnormal behavior.
[0061] The abnormal behavior detection method provided by the embodiment of the present invention is applied to an electronic device, and the electronic device may be a PC, a personal computer, or an image acquisition device.
[0062] The bayonet device installed at the intersection can obtain the video information of the vehicle passing the intersection, and the vehicle image in the video can...
Embodiment 2
[0071] In order to make it more accurate to determine whether the target object has abnormal behavior, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, before determining whether the target object has the abnormal behavior according to the intersection ratio, the method further includes :
[0072] Determine whether the abnormal behavior is a dominant abnormal behavior or a recessive abnormal behavior;
[0073] If the abnormal behavior is a dominant abnormal behavior, the determining whether the target object has the abnormal behavior according to the cross-combination ratio includes:
[0074] Judging whether the intersection-over-union ratio is greater than a preset first threshold, if yes, determining that the target object has the abnormal behavior;
[0075] If the abnormal behavior is a hidden abnormal behavior, the determining whether the target object has the abnormal behavior according to the cross-over-combination ratio inclu...
Embodiment 3
[0082] On the basis of the above-mentioned embodiments, in the embodiment of the present invention, the detection model includes a main network, a detection subnet and a classification subnet;
[0083] Based on the detection model, performing convolution processing on the first image, and determining the first feature map includes:
[0084] Based on the main network in the detection model, perform convolution processing on the first image, determine a first basic feature map, and input the first basic feature map into the detection subnetwork in the detection model; based on the The detection sub-network in the detection model performs convolution processing on the first basic feature map to determine the first feature map;
[0085] Before determining that the target object has the abnormal behavior, the method also includes:
[0086] Input the first basic feature map into the classification subnetwork of the detection model, and input the first feature map into the classific...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


