YOLOv8 Object Tracking using PyTorch, OpenCV and DeepSORT

This project imlements the following tasks in the project: 1. Vehicle counting, 2. Lane detection. 3.Lane change detection and 4.speed estimation

The main objective of this project is to identify overspeed vehicles, using Deep Learning and Machine Learning Algorithms. After acquisition of series of images from the video, trucks are detected using Haar Cascade Classifier. The model for the classifier is trained using lots of positive and negative images to make an XML file. This is followed by tracking down the vehicles and estimating their speeds with the help of their respective locations, ppm (pixels per meter) and fps (frames per second). Now, the cropped images of the identified trucks are sent for License Plate detection. The CCA (Connected Component Analysis) assists in Number Plate detection and Characters Segmentation. The SVC model is trained using characters images (20X20) and to increase the accuracy, 4 cross fold validation (Machine Learning) is also done. This model aids in recognizing the segmented characters. After recognition, the calculated speed of the trucks is fed into an excel sheet along with their license plate numbers. These trucks are also assigned some IDs to generate a systematized database.

Vehicle counting in a conjusted traffic road where background subtraction gives lower performance.

No description provided.

Vehicle detection and tracking and speed estimation using opencv

Traffic analysis using YOLOv4 and OpenCV

deepsort + yolov3 + velocity-tracker

Vehicle speed estimation using YOLOv9 for object detection and DeepSORT for tracking

Tracking, counting and speed estimation using yolo8

Speed estimation from a dash camera's feed using optical flow and CNN on Keras

University of Bristol MEng Computer Science Dissertation and Code for 'Predicting Ego-Vehicle Speed from Monocular Dash-Cam Video in Diverse Conditions'.

Speed Estimate

Vehicles speed detection and estimated speed tracking using Python with OpenCV and dlib libraries

Real-time object detection, speed estimation, and loitering detection system powered by YOLOv11 and accelerated with Hailo-8 NPU.

A script to track objects and estimate their speed in videos

This is an end-to-end traffic violation detection system in real time

A Tiny repo for solving the Vehicle Speed Estimation (car) problem based on Track 1 - AICity Challenge 2018

This repository contains everything to reproduce the gait speed sensor created in the LIARA Lab

Vehicle detection, tracking, counting, and speed estimation | project for the Vision & Cognitive Systems course (CompSci @ UniPd) | by Shakiba Farjood Fashalami and me

Repo of computer-vision/ML/DL project analysing football games

ZoneGuard - Real-time perimeter security system using YOLO11 for detecting persons entering restricted zones. Tracks movement with distance, speed, and duration analytics.

Synthetic underwater video generation and optical flow-based speed estimation pipeline for marine robotics and computer vision applications.

Intelligent aerial traffic monitoring system featuring real-time vehicle detection, tracking, speed estimation, and ALPR using YOLOv8.

A PyTorch model to estimate vehicle speed from video by feeding optical flow maps into a ResNet50-based regression network. Trained on the Comma.ai Speed Challenge dataset.

IU Projects

High-Precision Human Velocity Analysis Framework

Detects car speed using YOLOv8 and OpenCV, classifies vehicles as Passed or Failed, and saves annotated results.

Exploratory project into Vehicle Detection

This project utilizes YOLOv8 for object detection and tracking to estimate the speed of vehicles in real-time. The system identifies and tracks vehicles across frames and calculates their speed based on the displacement over time.