TFJS-object-detection
FastMOT
Our great sponsors
TFJS-object-detection | FastMOT | |
---|---|---|
1 | 2 | |
124 | 1,095 | |
- | - | |
0.0 | 0.0 | |
over 1 year ago | about 2 years ago | |
JavaScript | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
TFJS-object-detection
-
Cannot read property 'children' of undefined with using Tensorflow Object Detection API model in tfjs
Describe the current behavior I used transfer learning using a pretrained model from the Tensorflow Object Detection API, which i converted to tensorflow-js using the tensorflow-converter API in python. View the ipynb notebook HERE. I then followed @hugozanini's REPO which had a template for using your tensorflow object detection models in javascript; I copied the index.json file and put it into a sandbox, replacing his model.json file with mine. The repo which contains it can be found here
FastMOT
- Does Multi Object Tracking work better (precision/recall) on videos than jury rigging a SOTA image object detection to work on videos?
-
Assign ID and track moving object with optical flow
On failure, you can try using a re-identification methods like FastReid: https://github.com/JDAI-CV/fast-reid in combination with your detector. A good pipeline that combines everything you seem to need is here: https://github.com/GeekAlexis/FastMOT. It uses a combination of Yolov4 (detector) + Kalman filters, Optical flow (tracker) and FastReid (re-identification)
What are some alternatives?
handpose-facemesh-demos - 🎥🤟 8 minimalistic templates for tfjs mediapipe handpose and facemesh
multi-object-tracker - Multi-object trackers in Python
ybat - Ybat - YOLO BBox Annotation Tool
Deep-SORT-YOLOv4 - People detection and optional tracking with Tensorflow backend.
sharingan - Real-Time object detection app, built with Tensorflow.js.
ByteTrack - [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
ear-model-test - ear model test
fast-reid - SOTA Re-identification Methods and Toolbox
labelbox-custom-labeling-apps - Explore example custom labeling apps built with Labelbox SDK
zero-shot-object-tracking - Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.
mmtracking - OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
FairMOT - [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking