Convolutional Neural Networks-Based Object Detection Algorithm by Jointing Semantic Segmentation for Images

Sensors

Baohua Qiang¹  Yijie Zhai¹  Yuanchao Pang¹  Ruidong Chen¹  Minghao Yang¹  Mingliang Zhou² 

[1] Guangxi Colleges and Universities Key Laboratory of Intelligent Processing of Computer Image and Graphics, Guilin University of Electronic Technology, Guilin 541004, China;School of Computer Science, Chongqing University, 174 Shazheng Street, Shapingba District, Chongqing 400044, China;

关键词: object detection;    semantic segmentation;    attention mechanism;    hourglass network;    sensor;   

DOI  :  10.3390/s20185080

来源: DOAJ

【 摘 要 】

In recent years, increasing image data comes from various sensors, and object detection plays a vital role in image understanding. For object detection in complex scenes, more detailed information in the image should be obtained to improve the accuracy of detection task. In this paper, we propose an object detection algorithm by jointing semantic segmentation (SSOD) for images. First, we construct a feature extraction network that integrates the hourglass structure network with the attention mechanism layer to extract and fuse multi-scale features to generate high-level features with rich semantic information. Second, the semantic segmentation task is used as an auxiliary task to allow the algorithm to perform multi-task learning. Finally, multi-scale features are used to predict the location and category of the object. The experimental results show that our algorithm substantially enhances object detection performance and consistently outperforms other three comparison algorithms, and the detection speed can reach real-time, which can be used for real-time detection.

【 授权许可】

Unknown