Abstract
At present, a large number of off-line videos is stored in the server of surveillance network. In order to retrieve the target face in these massive videos frames, the face retrieval system is designed. A new Quadruplet Network is constructed by changing the RELU structure of CNN network and training the new Quadruplet Network to acquire the depth features. Join with the online fugitive face picture that launched online to initiate the wanted, with the help of the depth feature contrast to launch the Content-Based Image Retrieval (CBIR). The new Quadruplet Network converges faster than familiar networks such as Alexnet, Googlenet, VGGNet and ResNet. Because of the shared weight design of the network, the retrieval has a high precision, recall and the retrieval rate. Image depth features can be shared quickly online between the cameras. The experimental results show that the proposed method is effective, with an accuracy of 98.74% and a precision of 99.54%, and a frame rate of 28 FPS.
Highlights
At present, there are frequent crimes in our society
Based on the above three problems, this paper proposes a joint face retrieval network based on a new Quadruplet network in videos of multi-camera
The characteristics of Quadruplet network are explored, and the results show that the pre-processing methods, such as Batch Online Hard Negative Mining (OHNM), Subspace clustering and Focal Loss, can improve the sample difficulty of quaternion input, the efficiency of finding difficult samples and the balance of positive and negative samples
Summary
There are frequent crimes in our society. It is an important technical means for the police to obtain the evidence images from the video surveillance cameras. There are video surveillance cameras everywhere in the streets. The coverage area of the video surveillance cameras is very wide. High definition video surveillance cameras are collecting data all the time, and a large number of offline videos are produced every day. Take the HD camera for example, it produces 50-60 frames per second. The camera can record about 5 million frames of video in 24 hours, so the video data recorded by one camera in one month is very large. If you add up all the camera data in that area, it’s much more. For the criminal investigation department, it is obviously inefficient and painful to manually filter suspicious video frame by frame
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
