Implementing Multi-Object Tracking with ByteTrack and YOLOv8

Multi-Object Tracking (MOT) extends object detection by assigning a persistent ID to detected entities across video frames. While detection models like YOLO identify objects in individual frames, MOT ensures continuity, recognizing that an object in frame t is the same as in frame t+1. Algorithms such as SORT and DeepSORT have historically domi ...

Posted on Wed, 19 Aug 2026 16:08:54 +0000 by timgetback

Design of a Mobile Safety Inspection Robot with Computer Vision

Automated monitoring systems are increasingly vital in industrial construction environments to ensure personnel adhere to safety protocols, specifically regarding the use of protective gear like hard hats. This project outlines the development of a mobile inspection unit designed to detect helmet compliance using machine vision. The device util ...

Posted on Mon, 17 Aug 2026 16:49:38 +0000 by nick314

Image Segmentation Using Graph Cut and K-Means Clustering

Objective Understand graph cut operations and implement interactive segmentation by providing foreground and background markers on an image or selecting a region containing the foreground using a bounding box. Implement image segmentation using clustering methods (K-means algorithm). Implementation 1. Interactive Segmentation with Graph Cut I ...

Posted on Mon, 10 Aug 2026 16:43:28 +0000 by apaxson

Implementing a Handwritten Digit Recognition System Using the K-Nearest Neighbors Algorithm

This system is designed to recognize digits from 0 to 9. The input images are pre-processed to a uniform size of 32x32 pixels in black and white. For clarity, images are stored in a text format, despite not being memory efficient. Data Collection: Text File Format The dataset is adapted from the "Optical Recognition of Handwritten Digits&q ...

Posted on Sun, 09 Aug 2026 16:38:21 +0000 by Catfish

Building OpenCV 4.8 from Source on Ubuntu Systems

Downloading OpenCV 4.8 Source Execute the following commands in a terminal to download and extract the source code: wget -O opencv-4.8.zip https://github.com/opencv/opencv/archive/4.8.0.zip unzip opencv-4.8.zip -d opencv-4.8 Installing Build Dependencies Install required compliers and libraries using apt: sudo apt update sudo apt install -y bu ...

Posted on Fri, 31 Jul 2026 16:01:36 +0000 by Rithiur

Semi-Global Matching: Cost Volume Computation and Disparity Refinement

Cost Volume Initialization Census Transform The Census transform encodes local texture structure by comparing each neighbor pixel against the center pixel with in a window. This transform is robust to illumination variations since it only records relative intensity relationships. void computeCensusTransform(const uint8* input, uint32* census_ou ...

Posted on Wed, 22 Jul 2026 16:05:23 +0000 by seany123

Deepfake Detection Challenge: Baseline Implementation with EfficientNet

Data Preparation and Understanding Dataset Structure The competition provides training and validation datasets in the first phase. The training set (train_label.txt) is used for model training, while the validation set (val_label.txt) serves for hyperparameter tuning and model selection. Each line in these files contains two components: the ima ...

Posted on Tue, 14 Jul 2026 16:42:08 +0000 by Mr. R

Image Retrieval Using Color Histogram Features with MATLAB Implementation

Color Features Color represents one of the most fundamental visual attributes in digital images, effectively characterizing image content and distinguishing objects. Color histogram-based retrieval leverages the distribution of color values across an image to establish similarity between images. A color histogram is a multi-dimensional array wh ...

Posted on Sat, 11 Jul 2026 16:52:40 +0000 by fourteen00

Essential Camera Configuration and Vision Primitives for OpenMV

Camera Hardware Initialization and Configuration Proper setup of the image sensor is required before capturing frames. The following routiness manage hardware state and image acquisition parameters: sensor.reset(): Reinitializes the camera module to its default state. sensor.set_pixformat(fmt): Defines the color depth. Use sensor.GRAYSCALE for ...

Posted on Sat, 11 Jul 2026 16:20:02 +0000 by jaygattis

YOLOv9: A Comprehensive Guide to Setup, Training, and Inference

YOLOv9 represents a significant advancement in real-time object detection, distinguished by its innovative use of a purely convolutional architecture. Unlike many contemporary models that integrate Transformer layers, YOLOv9 achieves state-of-the-art performance, reportedly surpassing models like RT-DETR and even YOLOv8 across various benchmark ...

Posted on Sun, 05 Jul 2026 17:20:05 +0000 by mustng66