JinyuanLiu-CV/TarDAL
CVPR 2022 | Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection.
This project helps surveillance and security professionals improve object detection in challenging visual conditions, like low light or fog. It takes synchronized infrared and visible light images as input and combines them into a single, enhanced image that makes objects like people, cars, and trucks easier to spot and track. Users include security analysts, drone operators, and anyone relying on visual monitoring for safety or asset protection.
320 stars. No commits in the last 6 months.
Use this if you need to reliably detect objects in varied lighting and environmental conditions by leveraging both thermal and standard visual camera feeds.
Not ideal if you only have one type of image input (either infrared or visible) or if your primary goal is not object detection but rather general image enhancement.
Stars
320
Forks
52
Language
Python
License
GPL-3.0
Category
Last pushed
Aug 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/JinyuanLiu-CV/TarDAL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
drprojects/superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds