computer-vision
Real-Time Object Detection
3260 papers • 126 benchmarks • 313 datasets
Real-Time Object Detection is a computer vision task that involves identifying and locating objects of interest in real-time video sequences with fast inference while maintaining a base level of accuracy. This is typically solved using algorithms that combine object detection and tracking techniques to accurately detect and track objects in real-time. They use a combination of feature extraction, object proposal generation, and classification to detect and localize objects of interest. ( Image credit: CenterNet )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in real-time-object-detection
Trend
Dataset
Best Model
Actions
MS COCO
MS COCO
PASCAL VOC 2007
PASCAL VOC 2007
Argoverse-HD (Full-Stack, Val)
Libraries
iUse these libraries to find real-time-object-detection models and implementations
22 papers 12,921
Datasets
Subtasks
No subtasks available.
Most implemented papers
YOLOv3: An Incremental Improvement
Ali Farhadi, Joseph Redmon•Sat Apr 07 2018
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet, similar performance but 3.8x faster. As always, all the code is online at this https URL
