Research on Evaluation Technology of Police Robot Video and Image Application

Nowadays, intelligent technology is more and more widely used, especially in video and image area. The quality of the algorithm or model, as well as the adaptability to the application directly affects the output of the application software. Research institutions and development enterprises can find the flaws of their own technology through comprehensive evaluation. They can also find valuable research direction by observing the comprehensive performance evaluation results on the system platform and seeking technological innovation, thus promoting the overall progress of intelligent video application technology. The purpose of algorithm and system performance evaluation is to find the valuable direction by comparing the performance difference between algorithms and evaluating the level of detection or recognition technology. This paper proposes a series of evaluation methods and indexes for two kinds of intelligent video applications: face detection and recognition, object detection.

[1]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

[2]  James M. Rehg,et al.  Fast Asymmetric Learning for Cascade Face Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Zhi Tang,et al.  A Faster R-CNN Based Method for Comic Characters Face Detection , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[5]  Gengming Zhu,et al.  Joint Face Detection and Facial Expression Recognition with MTCNN , 2017, 2017 4th International Conference on Information Science and Control Engineering (ICISCE).

[6]  Xu Tang,et al.  PyramidBox: A Context-assisted Single Shot Face Detector , 2018, ECCV.

[7]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[8]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Larry S. Davis,et al.  SSH: Single Stage Headless Face Detector , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Fredric C. Gey,et al.  The relationship between recall and precision , 1994 .

[11]  Shuo Yang,et al.  Faceness-Net: Face Detection through Deep Facial Part Responses , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.