snenyl/realtime-pose-estimation
Realtime pose estimation using the YOLOX object detection algorithm and point cloud data from a Intel RealSense l515 RGB-D sensor.
This project helps operations managers and warehouse personnel accurately locate and orient logistics objects like pallets in real-time. By combining standard video with 3D depth data from an Intel RealSense l515 camera, it can detect an object's position and orientation. The output is a precise 3D pose, which can be used for automation in dynamic environments like warehouses.
Use this if you need to automate the precise identification and spatial understanding of objects like pallets in a warehouse or industrial setting using 3D sensing.
Not ideal if you only need basic object detection without 3D pose information, or if you're not working with Intel RealSense l515 depth sensors.
Stars
28
Forks
7
Language
C++
License
Apache-2.0
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/snenyl/realtime-pose-estimation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ultralytics/ultralytics
Ultralytics YOLO 🚀
Megvii-BaseDetection/YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX,...
kujason/avod
Code for 3D object detection for autonomous driving
aparsoft/yolo-streamlit-detection-tracking
Object detection and tracking algorithm implemented for Real-Time video streams and static images.
RizwanMunawar/yolov8-object-tracking
YOLOv8 Object Tracking Using PyTorch, OpenCV and Ultralytics