1
|
Camilleri MPJ, Zhang L, Bains RS, Zisserman A, Williams CKI. Persistent animal identification leveraging non-visual markers. MACHINE VISION AND APPLICATIONS 2023; 34:68. [PMID: 37457592 PMCID: PMC10345053 DOI: 10.1007/s00138-023-01414-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Revised: 05/29/2023] [Accepted: 06/12/2023] [Indexed: 07/18/2023]
Abstract
Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracking approaches unusable. However, a coarse estimate of each mouse's location is available from a unique RFID implant, so there is the potential to optimally combine information from (weak) tracking with coarse information on identity. To achieve our objective, we make the following key contributions: (a) the formulation of the object identification problem as an assignment problem (solved using Integer Linear Programming), (b) a novel probabilistic model of the affinity between tracklets and RFID data, and (c) a curated dataset with per-frame BB and regularly spaced ground-truth annotations for evaluating the models. The latter is a crucial part of the model, as it provides a principled probabilistic treatment of object detections given coarse localisation. Our approach achieves 77% accuracy on this animal identification problem, and is able to reject spurious detections when the animals are hidden.
Collapse
Affiliation(s)
| | - Li Zhang
- School of Data Science, Fudan University, Shanghai, China
| | | | - Andrew Zisserman
- Department of Engineering Science, University of Oxford, Oxford, UK
| | | |
Collapse
|
2
|
Fong T, Hu H, Gupta P, Jury B, Murphy TH. PyMouseTracks: Flexible Computer Vision and RFID-Based System for Multiple Mouse Tracking and Behavioral Assessment. eNeuro 2023; 10:ENEURO.0127-22.2023. [PMID: 37185293 PMCID: PMC10198609 DOI: 10.1523/eneuro.0127-22.2023] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2022] [Revised: 04/13/2023] [Accepted: 04/19/2023] [Indexed: 05/17/2023] Open
Abstract
PyMouseTracks (PMT) is a scalable and customizable computer vision and radio frequency identification (RFID)-based system for multiple rodent tracking and behavior assessment that can be set up within minutes in any user-defined arena at minimal cost. PMT is composed of the online Raspberry Pi (RPi)-based video and RFID acquisition with subsequent offline analysis tools. The system is capable of tracking up to six mice in experiments ranging from minutes to days. PMT maintained a minimum of 88% detections tracked with an overall accuracy >85% when compared with manual validation of videos containing one to four mice in a modified home-cage. As expected, chronic recording in home-cage revealed diurnal activity patterns. In open-field, it was observed that novel noncagemate mouse pairs exhibit more similarity in travel trajectory patterns than cagemate pairs over a 10-min period. Therefore, shared features within travel trajectories between animals may be a measure of sociability that has not been previously reported. Moreover, PMT can interface with open-source packages such as DeepLabCut and Traja for pose estimation and travel trajectory analysis, respectively. In combination with Traja, PMT resolved motor deficits exhibited in stroke animals. Overall, we present an affordable, open-sourced, and customizable/scalable mouse behavior recording and analysis system.
Collapse
Affiliation(s)
- Tony Fong
- Department of Psychiatry, University of British Columbia, Vancouver, British Columbia V6T 1Z3, Canada
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, British Columbia Canada V6T 1Z3
| | - Hao Hu
- Department of Psychiatry, University of British Columbia, Vancouver, British Columbia V6T 1Z3, Canada
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, British Columbia Canada V6T 1Z3
| | - Pankaj Gupta
- Department of Psychiatry, University of British Columbia, Vancouver, British Columbia V6T 1Z3, Canada
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, British Columbia Canada V6T 1Z3
| | - Braeden Jury
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, British Columbia Canada V6T 1Z3
| | - Timothy H Murphy
- Department of Psychiatry, University of British Columbia, Vancouver, British Columbia V6T 1Z3, Canada
- Djavad Mowafaghian Centre for Brain Health, University of British Columbia, Vancouver, British Columbia Canada V6T 1Z3
| |
Collapse
|
3
|
Han Y, Huang K, Chen K, Pan H, Ju F, Long Y, Gao G, Wu R, Wang A, Wang L, Wei P. MouseVenue3D: A Markerless Three-Dimension Behavioral Tracking System for Matching Two-Photon Brain Imaging in Free-Moving Mice. Neurosci Bull 2022; 38:303-317. [PMID: 34637091 PMCID: PMC8975979 DOI: 10.1007/s12264-021-00778-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2021] [Accepted: 06/23/2021] [Indexed: 10/20/2022] Open
Abstract
Understanding the connection between brain and behavior in animals requires precise monitoring of their behaviors in three-dimensional (3-D) space. However, there is no available three-dimensional behavior capture system that focuses on rodents. Here, we present MouseVenue3D, an automated and low-cost system for the efficient capture of 3-D skeleton trajectories in markerless rodents. We improved the most time-consuming step in 3-D behavior capturing by developing an automatic calibration module. Then, we validated this process in behavior recognition tasks, and showed that 3-D behavioral data achieved higher accuracy than 2-D data. Subsequently, MouseVenue3D was combined with fast high-resolution miniature two-photon microscopy for synchronous neural recording and behavioral tracking in the freely-moving mouse. Finally, we successfully decoded spontaneous neuronal activity from the 3-D behavior of mice. Our findings reveal that subtle, spontaneous behavior modules are strongly correlated with spontaneous neuronal activity patterns.
Collapse
Affiliation(s)
- Yaning Han
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Kang Huang
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Ke Chen
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
- University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Hongli Pan
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
| | - Furong Ju
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
| | - Yueyue Long
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
- University of Rochester, Rochester, NY, 14627, USA
| | - Gao Gao
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China
- Honam University, Gwangju, 62399, South Korea
| | - Runlong Wu
- State Key Laboratory of Membrane Biology, Institute of Molecular Medicine, Peking University, Beijing, 100101, China
| | - Aimin Wang
- Department of Electronics, Peking University, Beijing, 100871, China
- State Key Laboratory of Advanced Optical Communication Systems and Networks, Peking University, Beijing, 100101, China
| | - Liping Wang
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China.
- University of Chinese Academy of Sciences, Beijing, 100049, China.
| | - Pengfei Wei
- Shenzhen Key Laboratory of Neuropsychiatric Modulation and Collaborative Innovation Center for Brain Science, Guangdong Provincial Key Laboratory of Brain Connectome and Behavior, CAS Center for Excellence in Brain Science and Intelligence Technology, Brain Cognition and Brain Disease Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen-Hong Kong Institute of Brain Science, Shenzhen Fundamental Research Institutions, Shenzhen, 518055, China.
- University of Chinese Academy of Sciences, Beijing, 100049, China.
| |
Collapse
|
4
|
Nie S, Li Y, Ma B, Zhang Y, Song J. The Construction of Basketball Training System Based on Motion Capture Technology. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:2481686. [PMID: 34567479 PMCID: PMC8460370 DOI: 10.1155/2021/2481686] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/26/2021] [Revised: 08/25/2021] [Accepted: 08/27/2021] [Indexed: 11/17/2022]
Abstract
Motion capture is a cross-cutting application field developed in recent years, which comprises electronics, communications, control, computer graphics, ergonomics, navigation, and other disciplines. The accurate application of basketball technical movements in the basketball game is very important. Therefore, it is of great significance to capture and standardize athletes' movements and improve their training. Unfortunately, there are numerous issues in traditional classroom teaching that largely helps to train the athletes. To solve the issues of traditional basketball classroom teaching, a virtual simulation system for students' sports training is designed in this paper. Firstly, the information of basketball dribbling movement is captured and simulated in three dimensions. Secondly, we compare it with the standard database to judge the irregularities of athletes' movements, and carry out digital processing on athletes' movements and skill improvements statistics in combination with system functions. Thirdly, we set up a gradual training cycle. Finally, the Kinect-based capture technology is adopted to obtain the activity information of different joints of the human body. Through processing the motion data, relevant motion analysis data are fed to the established motion model, to realize the comparative analysis of motion pictures. In our experiments, we observed better training of the physical education.
Collapse
Affiliation(s)
- Shangqi Nie
- School of Physical Education, Huanghuai University, Zhumadian, China
- Department of Sports Science, Wonkwang University, Iksan-si, Republic of Korea
| | - Yuanqing Li
- School of Physical Education, Huanghuai University, Zhumadian, China
- Department of Sports Science, Wonkwang University, Iksan-si, Republic of Korea
| | - Biao Ma
- Department of Sports Science, Wonkwang University, Iksan-si, Republic of Korea
| | - Yufeng Zhang
- Department of Sports Science, Wonkwang University, Iksan-si, Republic of Korea
| | - Jeho Song
- Department of Sports Science, Wonkwang University, Iksan-si, Republic of Korea
| |
Collapse
|
5
|
Zheng L, Zhu Y, Yu H. Ideological and political theory teaching model based on artificial intelligence and improved machine learning algorithms. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021. [DOI: 10.3233/jifs-219127] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
In the era of artificial intelligence, traditional teaching models can be replaced by intelligent teaching models, thereby effectively improving the efficiency of ideological and political teaching. This paper proposes a multi-frame sliding window double-threshold clutter map CFAR algorithm and analyzes its detection probability and false alarm probability formula. Moreover, the ideological and political teaching system based on artificial intelligence and improved machine learning is designed based on the B/S model. In addition, this article analyzes the practical teaching performance of the model combined with actual teaching and analyzes the teaching effect of the model in ideological and political education. Through experimental research, it can be seen that the performance of the experimental group is significantly higher than that of the control group, which verifies that the algorithm constructed in this article has a certain practical effect.
Collapse
Affiliation(s)
- Lizhi Zheng
- Chengde Medical University, Hebei Chengde, China
| | - Yanjie Zhu
- Chengde Medical University, Hebei Chengde, China
| | - Hailong Yu
- Chengde Medical University, Hebei Chengde, China
| |
Collapse
|
6
|
Liu Y, Ji Y. Target recognition of sport athletes based on deep learning and convolutional neural network. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021. [DOI: 10.3233/jifs-189223] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
The main purpose of the various methods of evaluating athlete feature recognition is to monitor the current health of the athletes, thereby providing some feedback on the quality of individual training. Based on deep learning and convolutional neural networks, this paper studies athlete target recognition and proposes a feature vector extraction method based on curvature zero point. Moreover, based on the ideas of deep learning and convolutional neural networks, this paper builds an athlete feature recognition model and optimizes the algorithm. In order to verify the feasibility and efficiency of feature extraction algorithm of the sport athletes proposed by this paper and to facilitate comparison with other algorithms, this paper conducts an algorithm performance test on the sport athlete database. The research results show that the method proposed in this paper has certain advantages in the feature extraction of athletes and can be used in subsequent sports training systems.
Collapse
Affiliation(s)
- Yuzhong Liu
- College of Physical Education, Hubei Engineering University, Hubei, China
| | - Yuliang Ji
- College of Physical Education, Hubei University of Arts and Science, Hubei, China
| |
Collapse
|
7
|
Luo Y. Artificial intelligence model for real-time monitoring of ideological and political teaching system. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021. [DOI: 10.3233/jifs-189394] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
In ideological and political teaching, students have more serious problem behaviors in the classroom, including distracted, dazed, inattentive, and sleeping. In order to improve the efficiency of ideological and political teaching, based on artificial intelligence technology, this paper constructs a real-time monitoring system for ideological and political classrooms based on artificial intelligence algorithms, and builds model function modules according to the actual needs of ideological and political teaching monitoring. Moreover, this study makes reasonable calculations on the information monitoring and information transmission parts and installs a different number of monitoring equipment in different fixed locations according to the needs of signal monitoring. In addition, this paper designs a control experiment to study the system performance and verify the parameters from multiple aspects. The research results show that the system model constructed in this paper is stable in ideological and political teaching and has certain effects.
Collapse
Affiliation(s)
- Ying Luo
- Shijiazhuang University of Applied Technology, Shijiazhuang, Hebei, China
| |
Collapse
|
8
|
Chonggao P. Simulation of student classroom behavior recognition based on cluster analysis and random forest algorithm. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021. [DOI: 10.3233/jifs-189237] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Classroom student behavior recognition has important guiding significance for the development of distance education strategies. At present, the accuracy of students’ classroom behavior recognition algorithms has problems. In order to improve the effect of distance education student status analysis, this study combines the traditional clustering analysis algorithm and the random forest algorithm to improve the traditional algorithm and combines the human skeleton model to identify students’ classroom behavior in real time. Moreover, this research combines with the needs of students’ classroom behavior recognition to build a network topology model. The error rate of feature reconstruction using spatio-temporal features is lower than that of a single feature. Through experiments, this study verifies the effectiveness of the extracted spatial angle features based on the human skeleton model. The results of algorithm performance test show that the proposed algorithm network structure is superior to the network structure of single feature extraction algorithm.
Collapse
|
9
|
A novel low-noise movement tracking system with real-time analog output for closed-loop experiments. J Neurosci Methods 2019; 318:69-77. [PMID: 30650336 DOI: 10.1016/j.jneumeth.2018.12.016] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2018] [Revised: 12/16/2018] [Accepted: 12/20/2018] [Indexed: 11/24/2022]
Abstract
BACKGROUND Modern electrophysiological experiments are moving towards closing the loop, where the extrinsic (behavioral) and intrinsic (neuronal) variables automatically affect stimulation parameters. Rodent experiments targeting spatial behavior require animal 2D kinematics to be continuously monitored in a reliable and accurate manner. Cameras provide a robust, flexible, and simple way to track kinematics on the fly. Indeed, several available camera-based systems yield high spatiotemporal resolution. However, the acquired kinematic data cannot be accessed with sufficient temporal resolution for precise real-time feedback. NEW METHOD Here, we describe a novel software and hardware system for movement tracking based on color-markers with real-time low-noise output that works in both light and dark conditions. The analog outputs precisely represent 2D movement features including position, orientation, and their temporal derivatives, velocity and angular velocity. RESULTS Using adaptive windowing, contour extraction, and rigid-body Kalman filtering, a 640-by-360 pixel frame is processed in 28 ms with less than 4 ms jitter, for 100 frames per second. The system is robust to outliers, has low noise, and maintains a smooth, accurate output even when one or more markers are temporarily missing. Using freely-moving mice, we demonstrate novel applications such as replacing conventional sensors in a behavioral arena and inducing novel place fields via closed-loop optogenetic stimulation. COMPARISON WITH EXISTING METHOD(S) To the best of our knowledge, this is the first tracking system that yields analog output in real-time. CONCLUSIONS This modular system for closed-loop experiment tracking can be implemented by downloading an open-source software and assembling low-cost hardware circuity.
Collapse
|