Song Chengqun graduated from the School of Electronic Information Engineering at Sichuan University with a Ph.D. He completed his postdoctoral work at the Chinese Academy of Sciences. He is currently a senior engineer and doctoral supervisor at the Institute of Advanced Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences. He is recognized as a high-level professional talent in Shenzhen and a leading talent in Nanshan District, Shenzhen. He has received funding from the China Postdoctoral Science Foundation. He has participated in several national and provincial research projects, including the National Key Research and Development Program of the Ministry of Science and Technology, the Key Field R&D Program of the Guangdong Provincial Department of Science and Technology, and joint and general projects of the National Natural Science Foundation of China. He has led basic research projects and sub-projects of key basic research projects in Shenzhen. He has overseen the technical research and development of several horizontal projects commissioned by companies such as China Yangtze Power, China General Nuclear Power Group, Tencent, and Taishan Sports. He has developed a series of intelligent product prototypes and systems, including mobile robots, vision inspection systems, and interactive systems for nuclear power plants. He holds 15 authorized invention patents and has published over 20 high-level papers. His primary research areas are computer vision, deep learning, SLAM (Simultaneous Localization and Mapping), and robotics.
Research Areas
computer vision, deep learning, SLAM, robotics
Publications
Papers
[1] Chengqun Song, Bo Zeng, Jun Cheng, Fuxiang Wu, Fusheng Hao, PSMD-SLAM: Panoptic Segmentation-Aided Multi-Sensor Fusion Simultaneous Localization and Mapping in Dynamic Scenes, Applied Sciences, 14(9): 3843, 2024.
[2] Chengqun Song, Maolong Niu, Zhipeng Liu, Jun Cheng, Peng Wang, Hongjian Li, Luoying Hao, Spatial-temporal 3D dependency matching with self-supervised deep learning for monocular visual sensing, Neurocomputing, 481(7): 11-21, 2022.
[3] Chengqun Song, Bo Zeng, Tong Su, Ke Zhang, Jun Cheng, Data association and loop closure in semantic dynamic SLAM using the table retrieval method, Applied Intelligence, 52: 11472-11488, 2022.
[4] Tong Su, Shuo Ye, Chengqun Song*, Jun Cheng. Mask-Vit: An Object Mask Embedding in Vision Transformer for Fine-Grained Visual Classification, 29th IEEE International Conference on Image Processing, ICIP 2022, October 16, 2022 - October 19, 2022, Bordeaux, France: 1626-1630, 2022.
[5] Tong Su, Chengqun Song*, Jun Cheng. Vision Transformer Withinformation Bottleneck Forfine-Grained Visual Classification International Conference on Guidance, Navigation and Control, ICGNC 2022, August 5, 2022 - August 7, 2022, Harbin, China,845 LNEE: 4010-4019, 2023.
[6] Bo Zeng, Chengqun Song*, Cheng Jun, Yuhang Kang, DFPC-SLAM: A Dynamic Feature Point Constraints-Based SLAM Using Stereo Vision for Dynamic Environment, Guidance, Navigation and Control, 3(1): 2350003, 2023.
[7] Chengqun Song, Jun Cheng, Wei Feng, A Crowdsensing-based real time system for finger interactions in intelligent transport system, Wireless Communications and Mobile Computing, 2017: 7385052, 2017.
[8] Chengqun Song, Jun Cheng, A robust projector–camera interactive display system based on finger touch control by fusing finger and its shadow, Journal of the Society for Information Display, 25(9): 568-576, 2017.
[9]张可，宋呈群*，程俊，张锲石，曾驳，基于多目标快速探索随机树的移动机器人巡检路径优化方法，集成技术，2023，12(4): 32-41.
[10] Hushan Qin, Jun Cheng, Chengqun Song, Fusheng Hao, Qin Cheng. Structure-Preserving View-Invariant Skeleton Representation for Action Detection, 26th International Conference on Pattern Recognition, ICPR 2022, August 21, 2022 - August 25, 2022, Montreal, QC, Canada, 2022-August: 3190-3196, 2022.
[11] Zhen Liu, Jun Cheng, Libo Liu, Ziliang Ren, Qieshi Zhang, Chengqun Song, Dual-stream cross-modality fusion transformer for RGB-D action recognition, Knowledge-Based Systems, 255(14):109741, 2022.
[12] Zhen Liu, Qin Cheng, Chengqun Song, Jun Cheng. Cross-Scale Cascade Transforer for Multimodal Human Action Recognition. Pattern Recognition Letters, 168: 17-23, 2023.
[13] Fusheng Hao, Fuxiang Wu, Fengxiang He, Qieshi Zhang, Chengqun Song, Jun Cheng, Semantic-Aware Feature Aggregation for Few-Shot Image Classification, Neural Processing Letters, DOI: 10.1007/s11063-023-11150-2, 2023.
[14] 李雪松，张锲石，宋呈群，康宇航，程俊，自动驾驶场景下的轨迹预测综述，计算机工程，49(5): 1-11, 2023.
Patents
[1] Liu Zhenfei, Song Chengqun, Cheng Jun, Zhang Keshi, Gao Xiangyang, Guo Haiguang, A self-supervised multimodal scene depth estimation method and device, February 2, 2024, China, CN202410155848.5 [2] Gao Xiangyang, Cheng Jun, Zhang Keshi, Song Chengqun, Guo Haiguang, Qiao Enbao, Fang Zhibao, A two-wheeled electric vehicle charging system and its control method, November 17, 2023, China, CN202311551473.6 [3] Hao Fusheng, Wu Fuxiang, Zhang Keshi, Song Chengqun, Cheng Jun, A few-sample image recognition method, device, computer equipment, and storage medium, October 10, 2023, International, PCT/CN2023/123709 [4] Hao Fusheng, Wu Fuxiang, Zhang Keshi, Song Chengqun, Cheng Jun, A few-sample image recognition method, device, computer equipment, and storage medium, October 10, 2023, China, CN202311304784.2 [5] Wang Meiheng, Song Chengqun, Cheng Jun, A visual SLAM path planning method, device, electronic equipment, and storage medium, September 11, 2023, International, PCT/CN2023/118050 [6] Liu Zhenfei, Song Chengqun, Cheng Jun, A pose and depth map estimation method and system based on audio-visual knowledge distillation, September 11, 2023, China, CN202311170447.9 [7] Wang Meiheng, Song Chengqun, Cheng Jun, A visual SLAM path planning method, device, electronic equipment, and storage medium, September 11, 2023, China, CN202311170257.7 [8] Song Chengqun, Cheng Jun, Zhang Ke, Zeng Bo, Guo Haiguang, A mobile robot object target navigation method in an unknown environment, August 4, 2023, China, CN202310986396.0 [9] Zhang Ke, Song Chengqun, Cheng Jun, Guo Haiguang, Gao Xiangyang, Zeng Bo, An intelligent inspection method based on risk heat map, device, and electronic equipment, April 25, 2023, China, CN202310453915.7 [10] Zeng Bo, Song Chengqun, Cheng Jun, Wu Fuxiang, Hao Fusheng, A dynamic SLAM method, device, computer equipment, and storage medium, March 23, 2023, China, CN202310295336.4 [11] Qin Hu Shan, Cheng Jun, Song Chengqun, Hao Fusheng, Cheng Qin, A video action detection method, terminal, and storage medium, February 22, 2023, China, CN202310191382.X [12] Li Xuesong, Zhang Keshi, Cheng Jun, Song Chengqun, Gao Xiangyang, Guo Haiguang, A pedestrian trajectory prediction method, system, device, and storage medium, December 9, 2022, International, PCT/CN2022/137986 [13] Li Xuesong, Zhang Keshi, Cheng Jun, Song Chengqun, Gao Xiangyang, Guo Haiguang, A pedestrian trajectory prediction method, system, device, and storage medium, December 9, 2022, China, CN202211580181.0 [14] Zhang Ke, Song Chengqun, Cheng Jun, Zeng Bo, Qin Hu Shan, Liu Zhen, An inspection path processing method, device, equipment, and readable storage medium, July 7, 2022, China, CN202210794421.0 [15] Song Chengqun, Cheng Jun, Wu Fuxiang, Guo Haiguang, Gao Xiangyang, A guide method, device, and readable storage medium, June 24, 2022, International, PCT/CN2022/101093 [16] Song Chengqun, Cheng Jun, Wu Fuxiang, Guo Haiguang, Gao Xiangyang, A guide method, device, and readable storage medium, June 24, 2022, China, CN202210722609.4 [17] Liu Zhen, Cheng Jun, Ren Ziliang, Song Chengqun, Zhang Keshi, A multimodal information fusion recognition method and system based on attention mechanism, December 18, 2021, China, CN202111557072.2 [18] Cheng Jun, Song Chengqun, Zeng Bo, Wu Fuxiang, A robot control method and robot, December 12, 2021, International, PCT/CN2021/137304 [19] Su Tong, Song Chengqun, Cheng Jun, An image classification method based on a convolutional neural network-transformer hybrid architecture, December 6, 2021, China, CN202111479058.5 [20] Cheng Jun, Wu Fuxiang, Song Chengqun, A text-based image editing method and electronic device, October 12, 2021, International, PCT/CN2021/123272 [21] Cheng Jun, Wu Fuxiang, Song Chengqun, A text-based image editing method and electronic device, October 12, 2021, China, CN202111188395.9 [22] Zeng Bo, Song Chengqun, Cheng Jun, A visual SLAM method, device, terminal equipment, and storage medium, July 16, 2021, China, CN202110805748.9 [23] Cheng Jun, Song Chengqun, Zeng Bo, Wu Fuxiang, A robot control method and robot, April 21, 2021, China, CN202110428814.5 [24] Song Chengqun, Cheng Jun, 3D Semantic Map Construction Method and Module, Robot Interaction Method and System, December 8, 2020, China, CN202011442377.4 [25] Zhou Yichao, Cheng Jun, Wang Peng, Song Chengqun, Cheng Bo, Luan Yu, Wu Yiqian, Zhang Xuegang, Luan Zhenhua, A gesture control method, device, equipment, and storage medium for a nuclear power plant control system, November 12, 2020, China, CN202011260724.1 [26] Song Chengqun, Cheng Jun, A table retrieval-based simultaneous localization and mapping method and device, August 7, 2020, China, CN202010787859.7 [27] Luan Yu, Song Chengqun, Cheng Jun, Cheng Bo, Zhou Yichao, Wu Yiqian, Zhang Xuegang, Liu Zhiyang, Yu Zhenglong, Luan Zhenhua, A deep learning-based depth image acquisition method, device, equipment, and medium, December 4, 2019, China, CN201911225113.0 [28] Cheng Jun, Hu Ying, Song Chengqun, Yang Yuanyuan, A robot calibration method and terminal, October 28, 2019, China, CN201911028907.8 [29] Cheng Bo, Cheng Jun, Song Chengqun, Wang Peng, Zhou Yichao, Luan Yu, Wu Yiqian, Zhang Xuegang, Yu Zhenglong, Liu Zhiyang, Zhang Jianbo, Xu Xiaomei, Luan Zhenhua, A multi-channel fusion human-computer interaction method and system for a nuclear power plant control room, August 8, 2019, China, CN201910729952.X [30] Song Chengqun, Cheng Jun, Wang Peng, A neural network training method, device, and terminal equipment for scene cognition, June 28, 2019, China, CN201910573347.8 [31] Song Chengqun, Cheng Jun, Fang Jin, A camera-projector interactive touch device and system, June 28, 2017, China, CN201720775768.5 [32] Song Chengqun, Cheng Jun, Fang Jin, A camera-projector interactive touch method, device, and computer-readable storage medium, June 28, 2017, China, CN201710506544.9 [33] Song Chengqun, Cheng Jun, A panoramic 3D video stitching system and method, December 13, 2016, China, CN201611146790.X [34] Cheng Jun, Song Chengqun, Jiang Jun, An interactive projection method and device, November 24, 2016, China, CN201611050637.7