2022 4th International Conference on Robotics and Computer Vision (ICRCV)最新文献

Multiple Dynamic Object Tracking for Visual SLAM 基于视觉SLAM的多动态目标跟踪

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953172

Fuxin Liu Hubei, Yanduo Zhang, Xun Li

{"title":"Multiple Dynamic Object Tracking for Visual SLAM","authors":"Fuxin Liu Hubei, Yanduo Zhang, Xun Li","doi":"10.1109/ICRCV55858.2022.9953172","DOIUrl":"https://doi.org/10.1109/ICRCV55858.2022.9953172","url":null,"abstract":"The assumption based on scene rigidity has been accepted widely in visual SLAM framework. However, the supposition limits the development of SLAM algorithm in the real world. Especially for automatic driving, many complicate cases involved in it, which demands our SLAM system that provides accurate position robustly and perceives the surrounding environment reliably. Therefore, in this paper, we propose a novel visual SLAM front-end module, which uses instance segmentation and dense optical flow estimation to ensure the efficient separation of static background and dynamic targets. For potential moving objects, we take advantage of Unscented Kalman Filter (UKF) to track moving targets and update the according moving state. In light of scale inconsistency in the camera pose estimation, we recover the scene structure and obtain the scale factor in the key frame by the depth estimation network. At the end, we integrate the estimated camera pose and dynamic object tracking into a unified visual odometry. In the process of trajectory optimization, we adopt the sliding window mechanism to acquire the spatio-temporal information of the dynamic object. The experiment results show that the tracking of dynamic objects not only can provide rich clues for surroundings understanding, but also help the tracking of camera pose, and then improve the robustness of the SLAM system in dynamic environment.","PeriodicalId":399667,"journal":{"name":"2022 4th International Conference on Robotics and Computer Vision (ICRCV)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124263492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

An Efficient and Accurate 3D SLAM Method for Dynamic Environment 动态环境下一种高效准确的三维SLAM方法

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953253

Yingbo Wang, Zhong-li Wang, X. Wu

{"title":"An Efficient and Accurate 3D SLAM Method for Dynamic Environment","authors":"Yingbo Wang, Zhong-li Wang, X. Wu","doi":"10.1109/ICRCV55858.2022.9953253","DOIUrl":"https://doi.org/10.1109/ICRCV55858.2022.9953253","url":null,"abstract":"LiDAR-based 3D SLAM has always been one of the hotspots in the field of self-driving and mobile robots in the recent years. But how to build a robust and accurate map for a complex dynamic environment is still a challenging task, which attracts more and more attention in this community. In this paper, we proposed an efficient and accurate 3D SLAM method for complex dynamic environment, which mainly includes two stages. In the first moving object detection stage, an end-to-end full convolution semantic segmentation network (FCNN) is exploited to segment the potential moving objects accurately. Then the left point cloud is forward to the static SLAM module, which is based on direct point cloud registration method, the map is managed efficiently with the incremental kd-tree data structure. Additionally, an independent thread of the loop closure detection (LCD) based on the framework of multi-factor graph is adopted to further improve the accuracy and robustness of final outputs. With the elaborately design of the whole framework, the proposed method can work efficiently. The performance of the proposed method is validated with the benchmark dataset KITTI, the results show that by removing the dynamic objects, the stability and accuracy of SLAM can be greatly improved.","PeriodicalId":399667,"journal":{"name":"2022 4th International Conference on Robotics and Computer Vision (ICRCV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123011777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved Genetic-Ant Colony Fusion Algorithm 改进遗传-蚁群融合算法

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953222

Wei Hu, Tongzhou Zhao, Xin-wen Cheng, Chen Li

引用次数: 0

OA-STGCN: An Output Anchoring-based Graph Convolutional Network for Human Trajectory Prediction 基于输出锚定的人类轨迹预测图卷积网络

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953209

Jiuyu Chen, Zhong-li Wang, Jian Wang

引用次数: 0

Face Expression Recognition Based on Lightweight Fused Attention Mechanism 基于轻量级融合注意机制的人脸表情识别

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953221

Baocheng Yu, Guanyu Zhang, Wenxia Xu, Ming Wei

引用次数: 0

Context-Aware Network for Person Search 上下文感知网络的人员搜索

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953260

Yu Gu, Tao Lu

{"title":"Context-Aware Network for Person Search","authors":"Yu Gu, Tao Lu","doi":"10.1109/ICRCV55858.2022.9953260","DOIUrl":"https://doi.org/10.1109/ICRCV55858.2022.9953260","url":null,"abstract":"The key to effective person search is aiming to localize the pedestrians and obtain the discriminative embeddings representation for person ReID from numerous surveillance scene images. And the existing one-step anchor-free methods can achieve a trade-off between speed and accuracy, but it can not fully exploit the contextual feature information of search context, resulting in undesirable localization. To alleviate this issue, we propose a Context-Aware Network for Person Search (CANPS) to delve into the high-level contextual information. In CANPS, firstly, context encoder is proposed to bridge the gap between the feature maps, achieved by distributing rich contextual information to prediction head layers. Second, we design the malleable center sampling strategy to reasonably expose sample region and focus on the centroid feature representations. What’s more, we design above components in a trainable bag-of-freebies manner, so that real-time person search can greatly improve the accuracy without increasing extra inference cost. Extensive experiments show that the approach we proposed can outperform current state-of-the-art methods in public CUHK-SYSU datasets.","PeriodicalId":399667,"journal":{"name":"2022 4th International Conference on Robotics and Computer Vision (ICRCV)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124113010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Efficient CADNet for Classification of High-frequency Oscillations in Magnetoencephalography 脑磁图高频振荡分类的高效CADNet方法

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953255

Mei Zhang, Jun Liu, Chuang Liu, Ting Wu, Xueping Peng

{"title":"An Efficient CADNet for Classification of High-frequency Oscillations in Magnetoencephalography","authors":"Mei Zhang, Jun Liu, Chuang Liu, Ting Wu, Xueping Peng","doi":"10.1109/ICRCV55858.2022.9953255","DOIUrl":"https://doi.org/10.1109/ICRCV55858.2022.9953255","url":null,"abstract":"Epilepsy is a chronic neurological disease, and locating the lesions precisely is crucial to the success of epilepsy surgery. The high-frequency oscillations (HFOs) in magnetoencephalography (MEG) of epileptic patients can be used to detect seizures. Due to the inefficient and error-prone operation of traditional HFOs detection, it is necessary to develop an approach for the detection of HFOs, which can automatically classify HFOs in MEG. In this paper, We proposed a novel deep learning-based CADNet for the classification of HFOs in MEG. First, we preprocessed acquired MEG data by short-time Fourier transform (STFT), and the extracted time-frequency domain information was applied for model training after pictorialism. Then, we captured the features from these images through convolutional neural network combined with multi-head self-attention, all these features were input into Dendrite Net for classification. We evaluated our model on MEG dataset, and the accuracy, precision, recall, and F1-score of the optimized model reached 0.97, 0.98, 0.97, 0.97. We compared the proposed CADNet with other deep learning models, the result demonstrates that our model outperforms others.","PeriodicalId":399667,"journal":{"name":"2022 4th International Conference on Robotics and Computer Vision (ICRCV)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114500003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive Model-free Control with Supervising Switching Technique for Robotic Manipulator with Actuator Failure 机械臂失效的自适应无模型监督切换控制

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953229

Xingyu Ma, Haoping Wang, Yang Tian, Dingxin He

引用次数: 1

Multi-View Auto-Calibration Method Based on Human Pose Estimation 基于人体姿态估计的多视角自动校准方法

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953175

Lingling Chen, Zhuo Gong, Lifeng Li, Jian Yin

引用次数: 1

Research on Application of Bidirectional Thyristor in the Intelligent Air Filter 双向晶闸管在智能空气过滤器中的应用研究

2022 4th International Conference on Robotics and Computer Vision (ICRCV) Pub Date : 2022-09-25 DOI: 10.1109/ICRCV55858.2022.9953218

Min Zhang, Jing Wu, Chunmei Wang, Baocheng Yu, Wenxia Xu, Han Wang

{"title":"Research on Application of Bidirectional Thyristor in the Intelligent Air Filter","authors":"Min Zhang, Jing Wu, Chunmei Wang, Baocheng Yu, Wenxia Xu, Han Wang","doi":"10.1109/ICRCV55858.2022.9953218","DOIUrl":"https://doi.org/10.1109/ICRCV55858.2022.9953218","url":null,"abstract":"The bidirectional thyristor can be conducted bidirectionally and has good switching characteristics. The conversion from weak electricity to strong electricity and low power to high power can be realized via bidirectional thyristor. The intelligent air filter monitors indoor air quality and real-time control filer fan start-up and speed adjustment automatically according to the monitoring results. Therefore it can exchange the filtered outside air with the inside air.In the intelligent air filter, the zero-crossing detection circuit and the speed regulating circuit are designed. The zero-crossing Detection Circuit is realized by the photoelectric coupling device TLP521-2, and the accurate zero-crossing pulse is generated every time the power supply voltage passes the zero point. In the interrupt program, the I/O pin of the main control microcomputer is set to control the voltage of the fan to turn on and off, so as to realize the speed regulation.In the intelligent air filter, a total of 11 states are set. In each state, the proportion of different voltage connected, the fan can work at different speeds. When the voltage connected 20% , the speed is very low, increase in turn, when all connected, the speed is maximum. It has been proved by experiments that the characteristics of Sine curve of AC voltage can be guaranteed by half-waveguide pass. Fans can run continuously and stably under different settings, and the noise is even. So that fan speed regulation can be realized , no contact, quick action and high reliability.","PeriodicalId":399667,"journal":{"name":"2022 4th International Conference on Robotics and Computer Vision (ICRCV)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115940835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0