Pedestrian Detection Method Based on SSD Model

• 作者: Haijiang Hao Xiangao Luo Xin Li
• 来源期刊: 国际计算机前沿大会会议论文集
• 学科: 社会科学
• 关键词: PEDESTRIAN DETECTION SINGLE shot multibox DETECTOR model INCEPTION NETWORK
• 年，卷（期）: 2019,（1）
• 页码范围: 605-607
• 页数: 3页
• 分类号: C

摘要

Pedestrian detection has a wide range of applications in daily life, and many fields require pedestrians to conduct detection with high precision and speed, which is an urgent problem to be solved. The traditional pedestrian detection method improves the detection performance by improving the classification algorithm and extracting more effective features. In this paper, a pedestrian detection method is proposed based on single shot multibox detector (SSD) model, which replaces the basic network part of SSD model with inception network structure with smaller parameters, faster running speed and stronger nonlinear expression ability. A high-performance network model for pedestrian detection was based on improved SSD. The experimental results show that the proposed method is faster than the original model, and the average precision of pedestrian recognition and location is 89.6%, which is 2.6% higher than the original model.