A Joint Visual Compression and Perception Framework for Neuromorphic Spiking Camera
文献类型：期刊论文
| 作者 | Feng, Kexiang1,2; Jia, Chuanmin3; Ma, Siwei4,5; Gao, Wen4,5,6 |
| 刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
 |
| 出版日期 | 2025 |
| 卷号 | 34页码:4343-4356 |
| 关键词 | Image coding Cameras Feature extraction Encoding Visualization Distortion Decoding Binary sequences Video compression Vectors Spike compression visual intelligence end-to-end spike coding |
| ISSN号 | 1057-7149 |
| DOI | 10.1109/TIP.2025.3581372 |
| 英文摘要 | The advent of Neuromorphic spike cameras has garnered significant attention for their ability to capture continuous motion with unparalleled temporal resolution. However, this imaging attribute necessitates considerable resources for binary spike data storage and transmission. In light of compression and spike-driven intelligent applications, we present the notion of Spike Coding for Intelligence (SCI), wherein spike sequences are compressed and optimized for both bit-rate and task performance. Drawing inspiration from the mammalian vision system, we propose a dual-pathway architecture for separate processing of spatial semantics and motion information, which is then merged to produce features for compression. A refinement scheme is also introduced to ensure consistency between decoded features and motion vectors. We further propose a temporal regression approach that integrates various motion dynamics, capitalizing on the advancements in warping and deformation simultaneously. Comprehensive experiments demonstrate our scheme achieves state-of-the-art (SOTA) performance for spike compression and analysis. We achieve an average 17.25% BD-rate reduction compared to SOTA codecs and a 4.3% accuracy improvement over SpiReco for spike-based classification, with 88.26% complexity reduction and 42.41% inference time saving on the encoding side. |
| 资助项目 | Natural Science Foundation of China[62025101] ; Natural Science Foundation of China[62088102] ; Beijing Natural Science Foundation[4252003] ; Major Project of the National Social Science Foundation of China[24ZDA078] ; New Cornerstone Science Foundation through the Xplorer Prize |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001531746600002 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42094]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Jia, Chuanmin |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.Peking Univ, Wangxuan Inst Comp Technol, Beijing 100080, Peoples R China 4.Peking Univ, Natl Engn Res Ctr Visual Technol, Sch Comp Sci, Beijing 100871, Peoples R China 5.Peng Cheng Lab, Shenzhen 518055, Peoples R China 6.Chinese Acad Sci, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Feng, Kexiang,Jia, Chuanmin,Ma, Siwei,et al. A Joint Visual Compression and Perception Framework for Neuromorphic Spiking Camera[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2025,34:4343-4356. |
| APA | Feng, Kexiang,Jia, Chuanmin,Ma, Siwei,&Gao, Wen.(2025).A Joint Visual Compression and Perception Framework for Neuromorphic Spiking Camera.IEEE TRANSACTIONS ON IMAGE PROCESSING,34,4343-4356. |
| MLA | Feng, Kexiang,et al."A Joint Visual Compression and Perception Framework for Neuromorphic Spiking Camera".IEEE TRANSACTIONS ON IMAGE PROCESSING 34(2025):4343-4356. |
入库方式： OAI收割
来源：计算技术研究所
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。