Comments (2)
As far as the detection part is concerned, the cause is probably a too small number of training examples that have these features. I believe that, for example, static individuals are more likely to have these features, but are filtered out within datasets such as MOT16 and MOT20:
MOT16: A Benchmark for Multi-Object Tracking
This also affects the re-id part, as it may reduce the similarity between, for example, a person standing and squatting.
To improve this part, the appropriate way would be to finetune the model. Maybe an improvement could be achieved if static persons are not filtered out of the datasets.
Another option would be to use better alternatives to the kalman filter and hungarian algorithm.
from fairmot.
As far as the detection part is concerned, the cause is probably a too small number of training examples that have these features. I believe that, for example, static individuals are more likely to have these features, but are filtered out within datasets such as MOT16 and MOT20: MOT16: A Benchmark for Multi-Object Tracking This also affects the re-id part, as it may reduce the similarity between, for example, a person standing and squatting. To improve this part, the appropriate way would be to finetune the model. Maybe an improvement could be achieved if static persons are not filtered out of the datasets.
Another option would be to use better alternatives to the kalman filter and hungarian algorithm.
thanks,I will try it
from fairmot.
Related Issues (20)
- Error of running demo.py HOT 1
- No validation set was used for training
- RuntimeError: read(): fd 3 failed with Permission denied
- Why is this happening?
- Number of unique track ids in dataset zoo HOT 3
- RuntimeError: Error compiling objects for extension
- ModuleNotFoundError: No module named 'dcn_v2' HOT 3
- How to adjust detection box size?
- how to convert the images into video?
- Why do you filter ground truth data on the condition h > 0 and w > 0 in the JointDataset. HOT 1
- NaN id loss while training your custom dataset HOT 2
- Update 2DMOT15 references to MOT15 and fix broken link
- Default mot just installed using baseline
- How to add a plug-in
- Where can I find the pretrained dla34 model without dcn?
- ModuleNotFoundError: No module named '_ext'
- KeyError: 'epoch' by hrnetv2_w18_imagenet_pretrained.pth
- install torch1.7 in colab. HOT 1
- torch 1.7 in google colab HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fairmot.