Few-shot Object Counting and Detection (ECCV 2022)

Code for paper "From Crowd to Herd Counting: How to Precisely Detect and Count African Mammals using Aerial Imagery and Deep Learning?"

[ICCV 2023] Point-Query Quadtree for Crowd Counting, Localization, and More

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

This repository provides Computer Vision-based Vehicle Counting, an intelligent system created using Python-based computer vision techniques. The project leverages YOLOv8 for accurate vehicle detection and Sort for tracking. By integrating deep learning principles, the system can identify and count vehicles within a specified environment. Developme

Software for counting objects from drones

Project page for "OmniCount: Multi-label Object Counting with Semantic-Geometric Priors"

🚀 The TensorFlow Object Counting API is an open source framework built on top of TensorFlow and Keras that makes it easy to develop object counting systems!

Computer Vision and Deep Learning

ECCV24 - Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance

Object Detection and Counting in Videos using Yolov8. Includes training for new objects.

FishTally

real_time people counting in a fixed box

This project is an object detection and object counting tool built in Python. It uses computer vision techniques and deep learning models to detect objects in images and videos. The object detection is performed using the YOLO algorithm, and the object counting is done using OpenCV.

🚗 DinjanAI's Vehicle In/Out Detection & Count Project utilizes AI, ML, and DL to accurately track and count vehicles entering and exiting designated areas in real-time. Ideal for parking lots, intersections, and toll booths, it offers seamless integration and customizable configurations. 🛣️👀

Heatmap Learner Convolutional Neural Network for Object Counting and Localization

The objective is to count the plates using object detection and object tracking.

BMVC-2022 paper "Scale-Prior Deformable Convolution for Class-Agnostic Counting"(https://bmvc2022.mpi-inf.mpg.de/313)

Developed a comprehensive object detection and tracking project using YOLOv8 and the SORT algorithm for real-time tracking. Implemented both procedural and OOP approaches for maintainable code. Features include real-time detection, counting detected objects, and various output formats, with well-documented scripts for easy modification.