Object Detection Combining CNN and Adaptive Color Prior Features
文献类型：期刊论文
| 作者 | Gu, Peng1,2; Lan, Xiaosong1 ; Li, Shuxiao1,2
|
| 刊名 | SENSORS
 |
| 出版日期 | 2021-04-01 |
| 卷号 | 21期号:8页码:14 |
| 关键词 | convolutional neural network color prior model object detection |
| DOI | 10.3390/s21082796 |
| 通讯作者 | Li, Shuxiao(shuxiao.li@ia.ac.cn) |
| 英文摘要 | When compared with the traditional manual design method, the convolutional neural network has the advantages of strong expressive ability and it is insensitive to scale, light, and deformation, so it has become the mainstream method in the object detection field. In order to further improve the accuracy of existing object detection methods based on convolutional neural networks, this paper draws on the characteristics of the attention mechanism to model color priors. Firstly, it proposes a cognitive-driven color prior model to obtain the color prior features for the known types of target samples and the overall scene, respectively. Subsequently, the acquired color prior features and test image color features are adaptively weighted and competed to obtain prior-based saliency images. Finally, the obtained saliency images are treated as features maps and they are further fused with those extracted by the convolutional neural network to complete the subsequent object detection task. The proposed algorithm does not need training parameters, has strong generalization ability, and it is directly fused with convolutional neural network features at the feature extraction stage, thus has strong versatility. Experiments on the VOC2007 and VOC2012 benchmark data sets show that the utilization of cognitive-drive color priors can further improve the performance of existing object detection algorithms. |
| WOS关键词 | VISUAL-ATTENTION ; SCALE |
| 资助项目 | National Natural Science Foundation of China[U19B2033] ; National Natural Science Foundation of China[62076020] ; National Key RD Program[2019YFF0301801] |
| WOS研究方向 | Chemistry ; Engineering ; Instruments & Instrumentation |
| 语种 | 英语 |
| WOS记录号 | WOS:000644787200001 |
| 出版者 | MDPI |
| 资助机构 | National Natural Science Foundation of China ; National Key RD Program |
| 源URL | [http://ir.ia.ac.cn/handle/173211/44536]  |
| 专题 | 综合信息系统研究中心_脑机融合与认知评估 |
| 通讯作者 | Li, Shuxiao |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Gu, Peng,Lan, Xiaosong,Li, Shuxiao. Object Detection Combining CNN and Adaptive Color Prior Features[J]. SENSORS,2021,21(8):14. |
| APA | Gu, Peng,Lan, Xiaosong,&Li, Shuxiao.(2021).Object Detection Combining CNN and Adaptive Color Prior Features.SENSORS,21(8),14. |
| MLA | Gu, Peng,et al."Object Detection Combining CNN and Adaptive Color Prior Features".SENSORS 21.8(2021):14. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。