Understanding of Object Detection Based on CNN Family and YOLO

被引:175
作者
Du, Juan [1 ]
机构
[1] New Res & Dev Ctr Hisense, Qingdao 266071, Peoples R China
来源
2ND INTERNATIONAL CONFERENCE ON MACHINE VISION AND INFORMATION TECHNOLOGY (CMVIT 2018) | 2018年 / 1004卷
关键词
D O I
10.1088/1742-6596/1004/1/012029
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
As a key use of image processing, object detection has boomed along with the unprecedented advancement of Convolutional Neural Network (CNN) and its variants since 2012. When CNN series develops to Faster Region with CNN (R-CNN), the Mean Average Precision (mAP) has reached 76.4, whereas, the Frame Per Second (FPS) of Faster R-CNN remains 5 to 18 which is far slower than the real-time effect. Thus, the most urgent requirement of object detection improvement is to accelerate the speed. Based on the general introduction to the background and the core solution CNN, this paper exhibits one of the best CNN representatives You Only Look Once (YOLO), which breaks through the CNN family's tradition and innovates a complete new way of solving the object detection with most simple and high efficient way. Its fastest speed has achieved the exciting unparalleled result with FPS 155, and its mAP can also reach up to 78.6, both of which have surpassed the performance of Faster R-CNN greatly. Additionally, compared with the latest most advanced solution, YOLOv2 achieves an excellent tradeoff between speed and accuracy as well as an object detector with strong generalization ability to represent the whole image.
引用
收藏
页数:8
相关论文
共 25 条
[1]  
[Anonymous], 1961, PRINCIPLES NEURODYNA
[2]  
[Anonymous], PROC CVPR IEEE
[3]  
[Anonymous], 1982, Competition and Cooperation in Neural Nets, DOI DOI 10.1007/978-3-642-46466-9_18
[4]  
[Anonymous], PROC CVPR IEEE
[5]  
[Anonymous], IEEE T PATTERN ANAL
[6]  
[Anonymous], 2014, P 2 INT C LEARNING R
[7]   Object Detection with Discriminatively Trained Part-Based Models [J].
Felzenszwalb, Pedro F. ;
Girshick, Ross B. ;
McAllester, David ;
Ramanan, Deva .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (09) :1627-1645
[8]   COGNITRON - SELF-ORGANIZING MULTILAYERED NEURAL NETWORK [J].
FUKUSHIMA, K .
BIOLOGICAL CYBERNETICS, 1975, 20 (3-4) :121-136
[9]  
Giebel H., 1971, Pattern recognition in biological and technical systems, P162
[10]  
Girshick R.B., 2012, Discriminatively trained deformable part models, release 5