2D Object Detection
A computer vision task that localizes object bounding boxes in images and classifies them. Mainstream methods include Faster R-CNN, YOLO, and DETR, and a large number of pretrained models are available.
Timeline (last 90 days)
The 2D detection in the first stage of this approach does not require retraining or fine-tuning, and any off-the-shelf method that can produce 2D boxes and radar point associations can be directly plugged in.
Mainstream 2D object detection methods can be divided into two-stage detectors (such as Faster R-CNN) and one-stage detectors (such as YOLO, SSD, RetinaNet), as well as the Transformer-based DETR series.
All Facts (2)
The 2D detection in the first stage of this approach does not require retraining or fine-tuning, and any off-the-shelf method that can produce 2D boxes and radar point associations can be directly plugged in.
50%UnverifiedMainstream 2D object detection methods can be divided into two-stage detectors (such as Faster R-CNN) and one-stage detectors (such as YOLO, SSD, RetinaNet), as well as the Transformer-based DETR series.
50%