ABSTRACT
Aiming at the requirement of the mobile robot for the human-robot coexisting environment to distinguish people from objects and accurately estimate pedestrian pose and speed information in the indoor environment, the pedestrian detection and tracking method based on 2D Lidar and RGB-D camera is proposed. Firstly, 2D Lidar and environmental prior information are used to detect the position of leg features of the pedestrian. Then the RGB-D camera is used to detect the human skeleton features to obtain the pose of the pedestrian legs. Finally, based on the pedestrian constant velocity motion model and the observation model of leg feature, Kalman filter and global nearest neighbor data association are used to realize pedestrian motion state tracking. Experiments on the dataset demonstrate that the use of prior maps can reduce 2D Lidar false detections by 54.17% and improve the maximum and average persistent tracking time by 3.67 and 1.18 times. In the real scene experiment, the static pedestrian pose detection and the accurate tracking of the dynamic pedestrian are realized, which solves the problem that 2D Lidar cannot recognize the pose of humans when they are stationary.
- XAVIER J, PACHECO M, CASTRO D, Fast line, arc/circle and leg detection from laser scan data in a player driver[C]// 2005 IEEE International Conference on Robotics & Automation, Barcelona, Spain, 2005: 3402-3407.Google Scholar
- LU D V, SMART W D. Towards more efficient navigation for robots and humans[C]// 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, Tokyo, Japan, 2013:1707-1713.Google Scholar
- ARRAS K O, MOZOS O M, BURGARD W. Using boosted features for the detection of people in 2D range data[C]// 2007 IEEE International Conference on Robotics & Automation, Roma, Italy, 2007:3042-3407.Google Scholar
- LUCAS B, ALEXANDER H, TIMM L, Deep person detection in two-dimensional range data[J]. IEEE RA-L, 2018: 2726-2733.Google Scholar
- KOIDE K, MIURA J, MENEGATTI E. Monocular person tracking and identification with on-line deep feature selection for person following robot[J]. ROBOT AUTON SYST. 2020, 124: 103348.Google ScholarDigital Library
- LINDER T, BREUERS S, LEIBE B, On multi-modal people tracking from mobile platforms in very crowded and dynamic environments[C]// 2016 IEEE International Conference on Robotics & Automation, Stockholm, Sweden, 2016: 5512-5519.Google Scholar
- LEIGH A, PINEAU J, OLMEDO N, Person tracking and following with 2D laser scanners[C]// 2015 IEEE International Conference on Robotics & Automation, Seattle, Washington, 2015: 726-733.Google Scholar
- BELLOTTO N, HU H. Computationally efficient solutions for tracking people with a mobile robot: an experimental evaluation of Bayesian filters[J], AUTON ROBOT, 2010, 28(4): 425-438.Google ScholarDigital Library
- BELLOTTO N, HU H. Multisensor-based human detection and tracking for mobile service robots[J]. IEEE T SYST MAN CY B. 2009,39(1):167-181.Google ScholarDigital Library
- TRUONG X, YOONG V N, NGO T. RGB-D and laser data fusion-based human detection and tracking for socially aware robot navigation Framework[C]// Proceedings of the 2015 IEEE Conference on Robotics and Biomimetics, Zhuhai, China, 2015: 608-613.Google Scholar
- KONSTANTINOVA P, UDVAREV A, and SEMERDJIEV T. A study of a target tracking algorithm using global nearest neighbor approach[C]// Proceedings of the 4th International Conference on Computer Systems and Technologies, Rousse, Bulgaria, 2003: 290-295.Google Scholar
- ARRAS K O, GRZONKA S, LUBER M, Efficient people tracking in laser range data using a multi-hypothesis leg-tracker with adaptive occlusion probabilities[C]// 2008 IEEE International Conference on Robotics & Automation. Pasadena, USA, 2008: 1710-1715.Google Scholar
- SCHULZ D, BURGARD W, FOX D. People tracking with a mobile robot using sample-based joint probabilistic data association filters[J]. INT J ROBOT RES. 2003, 22(2):99-116.Google ScholarCross Ref
- ZHANG J, WANG W, QI X, Social and robust navigation for indoor robots based on object semantic grid and topological map[J]. Appl. Sci. 2020, 10(24), 8991.Google ScholarCross Ref
- Qi X, Wang W, Zhang X, Indoor topological map building with virtual door detection[J]. Journal of Jilin University )Engineering and Technology Edition(, 2021.Google Scholar
- Qi X, Wang W, Wang L, Semantic topological map building with object semantic grid map[J]. Journal of Jilin University )Engineering and Technology Edition(, 2021.Google Scholar
- CAO Z, HIDALGO G, SIMON T, OpenPose: Realtime multi-person 2D pose estimation using part affinity fields[J]. IEEE T PATTERN ANAL, 2021,43(1): 172-186.Google ScholarDigital Library
- BÁLVAREZ-APARICIO C, GUERRERO- HIGUERAS ÁM, OLIVERA MCC, Benchmark dataset for evaluation of range-based people tracker classifiers in mobile robots[J]. Front. Neurorobot, 2018, 11:72.Google ScholarCross Ref
Index Terms
- Pedestrian detection and tracking based on 2D Lidar and RGB-D camera
Recommendations
Robust pedestrian detection and tracking in crowded scenes
In this paper, a robust computer vision approach to detecting and tracking pedestrians in unconstrained crowded scenes is presented. Pedestrian detection is performed via a 3D clustering process within a region-growing framework. The clustering process ...
Robust pedestrian tracking using improved tracking-learning-detection algorithm
ICVGIP '16: Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image ProcessingManual analysis of pedestrians for surveillance of large crowds in real time applications is not practical. Tracking-Learning-Detection suggested by Kalal, Mikolajczyk and Matas [1] is one of the most prominent automatic object tracking system. TLD can ...
Combining patch matching and detection for robust pedestrian tracking in monocular calibrated cameras
This paper presents a new approach for tracking multiple people in monocular calibrated cameras combining patch matching and pedestrian detection. Initially, background removal and pedestrian detection are used in conjunction with the vertical standing ...
Comments