Knowledge Commons of Institute of Automation,CAS
Robust person head detection based on multi-scale representation fusion of deep convolution neural network | |
Wang Yingying1,2; Yin Yingjie1; Wu Wenqi1,2; Sun Siyang1,2; Wang Xingang1 | |
2017 | |
会议名称 | The IEEE International Conference on Robotics and Biomimetics (ROBIO) |
页码 | 296-301 |
会议日期 | 2017.12.5-2017.12.8 |
会议地点 | 澳门 |
摘要 |
Person head detection is still a challenge due to the large variability in heads’ sizes and orientations, lighting conditions and strong occlusions. Small heads require local information contained in low level layers instead of semantic features of upper layers. But most of these fine details are lost in the early convolutional layers of the deep convolution neural networks (DCNN). In order to improve the overall detection accuracy, it is important to utilize local information from lower layers into the detection framework. In this letter, we use multi-scale representation fusion of DCNN as a way to incorporate lower layers with upper layers for detection. Our proposed model is based on the recent object detection network Single Shot MultiBox Detector (SSD). VGG16 is used as the base network. Batch normalization (BN) layers are used in our proposed multi-task learning method to accelerate training process and improve the robustness. Compared to state-of-the-art methods, our proposed detector achieves superior person head detection performance on the HollywoodHeads dataset (81.0 AP) and Casablance dataset (78.5 AP). |
关键词 | Person Head Detection Deep Convolution Neural Network Multi-scale Representations Multi-task Learning |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/19753 |
专题 | 中科院工业视觉智能装备工程实验室_精密感知与控制 |
作者单位 | 1.自动化研究所精密感知与控制研究中心 2.中国科学院大学 |
第一作者单位 | 精密感知与控制研究中心 |
推荐引用方式 GB/T 7714 | Wang Yingying,Yin Yingjie,Wu Wenqi,et al. Robust person head detection based on multi-scale representation fusion of deep convolution neural network[C],2017:296-301. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ROBIO.pdf(673KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论