bounding-box-regression

目标检测 - R-CNN算法实现

IOU as loss for object detection tasks and IOU as metric for object detection tasks

This program shows how Bounding-Box-Regression works in a visual form. Intersection over Union ( IOU ), Non Maximum Suppression ( NMS ), Object detection, 边框回归，边框回归可视化，交并比，非极大值抑制，目标检测。

Project Idea is to train an object detection model which can detect humans in a video and results in all the bounding boxes with humans upon which I have calculated the distance between boxes. Bounding boxes in closer than a threshold value are classified with different color. Also created Bird's eye view using which we can avoid overlapping.

GUI for Bounding Box creation used in Object Detection Purposes

segXray - Bounding box prediction for 14 different findings in chest X-ray images

PyTorch implementation of single-object localization using a pretrained EfficientNet-B0 model for bounding box regression, with Albumentations-based geometric augmentation and custom dataset pipeline.

CNN model to detect license plates on cars

Multi-output CNN for joint image classification and bounding box regression. Deep Learning exam project — Bachelor's in AI from the joint Universities of Pavia, Milano-Bicocca, Milano Statale.

Single-object detection in PyTorch: a ResNet18 backbone with separate classification and box-regression heads, trained on a fixed 6,200-scene composited dataset and compared against a fine-tuned YOLOv8n.