A Target Detection Model Based on Improved Tiny-Yolov3 Under the Environment of Mining Truck

• Main Authors: Dong Xiao, Feng Shan, Ze Li, Ba Tuan Le, Xiwen Liu, Xuerao Li
• Format: Article
• Language: English
• Published: IEEE 2019-01-01
• Series: IEEE Access
• Subjects: Convolutional neural network; real-time; residual network; target detection; tiny-yolov3
• Online Access: https://ieeexplore.ieee.org/document/8762130/

In the open pit mine production systems, a certain number of trucks transport mine and rock between the power shovel and the unloading point. Due to the mining truck has characteristics of high height, long width and big size, it has a large blind zone and a long braking distance. Therefore, the probability of accidents in mining trucks is high, which results in huge loss of manpower, material resources and financial resources. In this paper, tiny-yolov3 is used to detect obstacles in the mine, its real-time performance is high enough, but the detection accuracy is not ideal. Therefore, this paper proposes an improved target detection model based on tiny-yolov3. The residual network structure based on convolutional neural network is added to the tiny-yolov3 structure, and the accuracy of obstacle detection is improved under the condition of real-time detection. The experimental results show that compared with tiny-yolov3, the detect precision of tiny-yolov3 with residual structure is improved, and the detection speed is reduced slightly, there is no particular impact on the real-time nature of the entire algorithm.