BROWSE
Detail
Conference Paper
Performance Enhancement of YOLOv3 by Adding Prediction Layers with Spatial Pyramid Pooling for Vehicle Detection
Cited 45 time in 
Download 13 time
Share 
Download 13 time
Share
- Authors
- Kwang-Ju Kim, Pyong-Kun Kim, Yun-Su Chung, Doo-Hyun Choi
- Issue Date
- 2018-11
- Citation
- International Conference on Advanced Video and Signal-based Surveillance (AVSS) 2018, pp.411-416
- Language
- English
- Type
- Conference Paper
- Project Code
- 18ZD1100, Development of ICT Convergence Technology for Daegu-GyeongBuk Regional Industry, Moon Ki Young
- Abstract
- In recent years, vision-based object detection methods using convolutional neural network (CNN) have been very successful. However, the object detection method using the CNN feature has a disadvantage that lots of feature maps should be generated in order to be robust against the scale change and the occlusion of the object. Also, simply raising a large number of feature maps does not improve performance. We propose a multi-scale vehicle detection with spatial pyramid pooling method which is robust to the scale change of the vehicle and the occlusion by improving the conventional YOLOv3 algorithm. The proposed method was evaluated through the UA-DETRAC benchmark and obtain the state-of-the-art mAP, which is better than those of the DPM, ACF, R-CNN, CompACT, NANO, SA-FRCNN, and Faster-RCNN2.
- KSP Keywords
- CNN features, Convolution neural network(CNN), Detection Method, Feature Map, Multi-scale, Pooling method, R-CNN, Spatial Pyramid Pooling, Vehicle detection, performance enhancement, state-of-The-Art