apennisi / Jpdaf_tracking
Licence: gpl-3.0
A tracker based on joint probabilistic data association filtering.
Stars: ✭ 107
Projects that are alternatives of or similar to Jpdaf tracking
Monocular Visual Odometry
A simple monocular visual odometry (part of vSLAM) by ORB keypoints with initialization, tracking, local map and bundle adjustment. (WARNING: Hi, I'm sorry that this project is just tuned for course demo, not for real world applications !!!)
Stars: ✭ 147 (+37.38%)
Mutual labels: opencv, tracking, eigen
Person Detection And Tracking
A tensorflow implementation with SSD model for person detection and Kalman Filtering combined for tracking
Stars: ✭ 193 (+80.37%)
Mutual labels: opencv, tracking
Multi Camera Live Object Tracking
Multi-camera live traffic and object counting with YOLO v4, Deep SORT, and Flask.
Stars: ✭ 375 (+250.47%)
Mutual labels: opencv, tracking
Co Fusion
Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
Stars: ✭ 400 (+273.83%)
Mutual labels: fusion, tracking
Poseflow
PoseFlow: Efficient Online Pose Tracking (BMVC'18)
Stars: ✭ 330 (+208.41%)
Mutual labels: opencv, tracking
Maskfusion
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
Stars: ✭ 404 (+277.57%)
Mutual labels: fusion, tracking
Curved Lane Lines
detect curved lane lines using HSV filtering and sliding window search.
Stars: ✭ 100 (-6.54%)
Mutual labels: opencv
Captchouli
booru-backed procedurally-generated anime image captcha library and server
Stars: ✭ 104 (-2.8%)
Mutual labels: opencv
Fusionjs
Modern framework for fast, powerful React apps
Stars: ✭ 1,353 (+1164.49%)
Mutual labels: fusion
Sign Language Recognition
✌️ 👌 ✊ 📷 Sign Language Recognition using Python
Stars: ✭ 98 (-8.41%)
Mutual labels: opencv
Selfdrivingcar
A collection of all projects pertaining to different layers in the SDC software stack
Stars: ✭ 107 (+0%)
Mutual labels: opencv
Arkit Multiplayer
ARKit multiplayer experience explanation & example
Stars: ✭ 106 (-0.93%)
Mutual labels: opencv
Synthesis
A robot simulator which exports a CAD model into a physics environment
Stars: ✭ 101 (-5.61%)
Mutual labels: fusion
Pedestriancounter
Pedestrians detection and tracking using OpenCV on Python
Stars: ✭ 100 (-6.54%)
Mutual labels: opencv
Hiitpi
A workout trainer Dash/Flask app that helps track your HIIT workouts by analyzing real-time video streaming from your sweet Pi using machine learning and Edge TPU..
Stars: ✭ 106 (-0.93%)
Mutual labels: opencv
Imagestitching
Conducts image stitching upon an input video to generate a panorama in 3D
Stars: ✭ 98 (-8.41%)
Mutual labels: opencv
Opencv3 Intro Book Src
📘《OpenCV3编程入门》书本配套源码 |《Introduction to OpenCV3 Programming》Book Source Code
Stars: ✭ 1,369 (+1179.44%)
Mutual labels: opencv
Awesome Face Detection
Compare with various detectors - s3fd, dlib, ocv, ocv-dnn, mtcnn-pytorch, face_recognition
Stars: ✭ 106 (-0.93%)
Mutual labels: opencv
Joint Probabilistic Data Association Tracking (JPDAFTracker)
JPDAFTracker is a tracker based on joint probabilistic data association filtering.
Requirements
- OpenCV
- Eigen
How to build
JPDAFTracker works under Linux environments. I recommend a so-called out of source build which can be achieved by the following command sequence:
- mkdir build
- cd build
- cmake ../
- make -j<number-of-cores+1>
Params
[PD] #DETECTION PROBABILITY
1
[PG] #GATE PROBABILITY
0.4
[LOCAL_GSIGMA] #THRESHOLD OF GATING
15
[LOCAL_ASSOCIATION_COST] #ASSOCIATION COSTS
40
[GLOBAL_GSIGMA] #THRESHOLD OF GATING
0.1
[GLOBAL_ASSOCIATION_COST] #ASSOCIATION COSTS
50
[LAMBDA] #CONSTANT
2
[GAMMA] #G1,G2 INITIAL COVARIANCE P MATRIX
10 10
[R_MATRIX] #2x2 MEASUREMENT NOISE COVARIANCE MATRIX
100 0
0 100
[DT] #dt
0.4
[MIN_ACCPETANCE_RATE] #min rate for convalidating a track
10
[MAX_MISSED_RATE] #max rate for deleting a track
9
How to use
Go to the bin diretory and launch the program with the following command:
./jpdaf_tracker ../config/kalman_param.txt /path/to/the/detection_file.txt /path/to/the/image_folder
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].