baidut / baidut/OpenVehicleVision

标注显示工具

Open
#26 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
No language data
Stars
136
Forks
57
PR merge metrics
No merged PRs in 30d

Description

- [ ] 多类别的GT
- [ ] 单个图片处理和视频处理
- [x] 突出GT边缘
- [ ] 结果对比,和GT对比的漏报和错检
- [ ] 多个结果对比,多的漏报(越少越好)和多的错检(越少越好)

三种方式显示GT标注,目前仅支持两类识别的GT

![image](https://cloud.githubusercontent.com/assets/6234266/13427228/909be700-dfed-11e5-8a9c-3a90cab8184b.png)

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating the MATLAB code for displaying ground-truth annotations, since no specific file or test is named. Review how the current two-class display works, then define the scope for multiclass ground truth, single-image and video processing, and result comparisons. Done should cover the unchecked checklist items with verifiable comparisons of missed detections and false positives.

Written by the indexing model from the issue text.

Assessment

Tech stack
matlab
Domain
computer-vision, tooling
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.