Summary of Bangladeshi Native Vehicle Detection in Wild, by Bipin Saha et al.
Bangladeshi Native Vehicle Detection in Wild
by Bipin Saha, Md. Johirul Islam, Shaikh Khaled Mostaque, Aditya Bhowmik, Tapodhir Karmakar Taton, Md. Nakib Hayat Chowdhury, Mamun Bin Ibne Reaz
First submitted to arxiv on: 20 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Bangladesh Native Vehicle Dataset (BNVD) aims to address the scarcity of region-specific vehicle detection datasets, which hinders the development of context-aware autonomous navigation systems. The BNVD dataset consists of 17326 images with fully annotated instances of 17 distinct vehicle classes, covering various geographical, illumination, and orientation conditions. To evaluate the effectiveness of the BNVD dataset, four YOLO models (YOLO v5, v6, v7, and v8) are compared, yielding a mean average precision (mAP) of 0.848 at an intersection over union (IoU) threshold of 50%. The results indicate that the BNVD dataset provides a reliable representation of vehicle distribution and presents considerable complexities. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new vehicle detection dataset for Bangladesh, which is important because autonomous vehicles need to recognize different types of vehicles in specific regions. The dataset has many images with labeled vehicles, covering various conditions like day and night, different sizes, and orientations. The researchers tested four YOLO models on this dataset and found that it’s effective for recognizing vehicles. |
Keywords
» Artificial intelligence » Mean average precision » Yolo
