Improvements of YoloV3 for road damage detection
Qinglang Wang, Jingchao Mao, Xu Zhai, Jie Gui, Wenjie Shen, Ye Liu
Abstract
Abstract Automatic detecting road damage from images is a challenging problem. Recent advances in deep learning based detectors offer a powerful tool for resolving this problem. However, these deep learning detectors are designed for detecting generic objects, the specific characteristics of road damage are not considered in these methods. We propose in this paper an improved method based on YoloV3 that takes in consideration the slenderness and tininess nature of the road damage, which require low-level and detailed description. Our method fuses the low-level feature with high level feature to enhance the description power of the network, and also an improvement to the loss function further boosts the detection performance. Experimental results have demonstrated the effectiveness of proposed method.