Images

5471 images

Explore Dataset

Project Overview

Objective: To develop a computer vision model that utilizes YOLO v8 to detect various types of construction vehicles. Background: Construction sites typically have a variety of vehicles, like dump trucks, excavators, and cranes. Manual monitoring is labor-intensive and error-prone. YOLO (You Only Look Once) v8 is chosen for its speed and accuracy in object detection.

Methodology

Data Collection: Gather labeled images of construction vehicles from various angles and lighting conditions, ensuring diversity. Data Pre-processing: Annotate objects, resize images, and augment the dataset. Model Training: Implement YOLO v8 in Python, train the model, and validate its performance. Evaluation: Assess model performance using precision, recall, and F1 score, and conduct real-world tests. Deployment: Integrate the model into a user-friendly interface for construction management students, with documentation and tutorials.

Expected Outcomes A high-accuracy model for detecting multiple types of construction vehicles. Enhanced monitoring on construction sites for improved safety and efficiency. An accessible tool for construction management students to gain practical computer vision experience.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{
                            iht-lab-con-v2_dataset,
                            title = { IHT LAB CON+ V2 Dataset },
                            type = { Open Source Dataset },
                            author = { 603 },
                            howpublished = { \url{ https://universe.roboflow.com/603/iht-lab-con-v2 } },
                            url = { https://universe.roboflow.com/603/iht-lab-con-v2 },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2024 },
                            month = { mar },
                            note = { visited on 2024-04-29 },
                            }