experiencor/image-to-3d-bbox
Build a CNN network to predict 3D bounding box of car from 2D image.
Automatically identify and outline the 3D dimensions of cars shown in 2D images or video frames. You provide standard images, and it outputs the precise 3D bounding box coordinates for each car, allowing for accurate spatial understanding. This is ideal for autonomous vehicle developers or advanced robotics engineers working with visual scene perception.
243 stars. No commits in the last 6 months.
Use this if you need to accurately determine the real-world 3D size and position of vehicles from camera footage.
Not ideal if you are looking to identify general objects, or if 2D object detection is sufficient for your needs.
Stars
243
Forks
55
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 09, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/experiencor/image-to-3d-bbox"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
JaFro96/streets-in-qatar
Detecting streets in the area of the Khalifa International Stadium. A deep learning approach...
Samia35-2973/Deep-Learning-for-Explainable-Traffic-Anomaly-Detection-in-Dhaka
The project introduces a Multi-Stage Traffic Anomaly Analysis Framework for identifying and...
ViniciusN12/TCC1_Vinicius
Solução de visão computacional para o agronegócio utilizando YOLOv8 e DeepSORT. Realiza detecção...