Interactive Deep Learning System for Automated Car Damage Detection: Multi-Model Evaluation and Interactive Web Deployment

Опубликована: Май 8, 2025

This project presents an automated framework for vehicle damage evaluation employing deep learning methodologies, designed to optimize assessment procedures within automotive service environments. By implementing the YOLOv9 computational vision architecture, system enables rapid identification of vehicular components through advanced pattern recognition, reducing reliance on labor-intensive manual inspections. The model underwent training extensive curated dataset comprising 8,450 annotated images capturing diverse morphologies across multiple perspectives, including frontal collisions, lateral impacts, and rear-end accidents. integrates physics-informed augmentation strategies enhance environmental adaptability, particularly addressing challenges posed by variable lighting conditions reflective surfaces. A modular processing pipeline facilitates scalable deployment quantization techniques optimized edge computing devices, demonstrating practical applicability in center operations. incorporates a web-based interface enabling real-time visualization report generation, significantly streamlining technician workflows. Experimental results indicate substantial improvements inspection efficiency, with architecture achieving 87% mean average precision ([email protected]) while maintaining efficiency. Quantized variants exhibited 68% reduction memory footprint minimal accuracy degradation. Field validations conducted centers confirmed system's operational effectiveness, highlighting strong correlations between complexity, duration, detection capabilities. research establishes foundational insights future advancements 3D reconstruction adaptive systems diagnostics.

Язык: Английский

---

CES: Cost Estimation System for Enhancing the Processing of Car Insurance Claims

Journal of Computing and Communication, Год журнала: 2024, Номер 3(1), С. 55 - 69

Опубликована: Янв. 31, 2024

Damage assessment is crucial in determining insurance reimbursements the car industry. However, manual inspection time-consuming and financially costly. Artificial Intelligence (AI) offers a promising automatic damage solution; we propose Cost Estimation System (CES) for volume level recognition cost estimation. CES extracts estimates from mobile imagery data combines them with structured customer to generate accurate purposes. This paper adopts CRISP-DM (Cross Industry Standard Process Data Mining) methodology develop robust systematic model. Leveraging AI technology such as (You Only Look Once) YOLO model Transformers image classification while expediting claims process mitigating fraud risk. Evaluating performance indicates ability accurately identify locate damaged regions images, an average precision of 78.50%, recall 70.24%, mean Average Precision (mAP) 0.66. Resulting satisfactory curated dataset 2508 photos, which classified by body parts, their inspected parts enhancing estimation, productivity, accuracy, time savings.

Язык: Английский

---

CDA-Net: Computer Vision based Automatic Car Damage Analysis

Опубликована: Дек. 15, 2023

Car insurance claims are rising in tandem with the tide of car users. Every claim requires an engineer's manual assessment and a surveyor's actual examination. This procedure can last anywhere from few days to several weeks. Current deep-learning techniques have paved way for this type mechanization. Both business client would benefit comprehensive system. To assess damage cost process, make model car, damaged parts, type, severity important parameters. We introduced two datasets, piqued (CMM) dataset containing images most popular 23 makes 148 vehicle models available Indian automotive market. The second consists 11,380 collected offices web resources different types damage, including annotations. In addition, it provides each part, (dents, scratches, bent, broken, cracks, smashed, punched, pushed), location (front, back, side). helps estimate when combined structured data. proposed CDA_YOLOv5 framework outperformed existing state-of-the-art one-stage average per-class accuracy 87.36% overall 90.45%.

Язык: Английский

---

Car Body Damage Detection System Using YOLOv7

Опубликована: Авг. 9, 2023

Car damage inspection is an important step when submitting car insurance claims. Currently, companies manually gather assessment reports. However, this approach takes a lot of time and susceptible to fraud. Advances in data science artificial intelligence offer solutions for automated systems detection. This system can detect classify different types damage. Implementation reduce operational costs, save time, minimize leakage. In study, we proposed object detection algorithm that YOLOv7 automate Three variations from the will be used paper. There are YOLOv7-tiny, YOLOv7, YOLOv7x. Our experiment shows YOLOv7x achieved greatest performance with validation F1-score 0.949

Язык: Английский

---

Detection and Localization of Car Damages Using Deep Learning

Опубликована: Ноя. 21, 2024

Язык: Английский

---