Dataset Information

DATS_2022: A versatile indian dataset for object detection in unstructured traffic conditions

ABSTRACT: Driver Assistance System has proved to be the best alternative to the autonomous vehicles in countries like India which has heavy and irregular traffic conditions. It is a challenging task for a machine to visually understand the traffic scenes in a complex environment. To develop a machine learning algorithm for such an environment, there is a need of a dataset that may provide the correct information of the traffic scene. The proposed dataset, DATS_2022, is a comprehensive dataset for object detection specific to Indian traffic scenario. The dataset consists of images captured using a high-resolution camera in an android phone. The images are annotated using a free, open-source tool. XML files for these annotations are generated and saved which are used to extract the labels for training various machine learning algorithms. DATS_2022 is a complete dataset with images from rural as well as urban Indian traffic scenes. The dataset consists of more than 10000 images with 45object classes. There are more than 7000 annotations in different formats along with the dataset till the submission of this work. It aims to support research in the area of object detection and classification using deep and machine learning algorithms.

SUBMITTER: Paranjape B

PROVIDER: S-EPMC9309657 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The computer vision systems driving autonomous vehicles are judged by their ability to detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing this ability of a self-driving car to distinguish between the elements of its environment under adverse conditions is an important challenge in computer vision. For example, poor weather conditions like fog and rain lead to image corruption which can cause a drastic drop in object detection (OD) performance. The primary navigation of autonomous vehicles depends on the effectiveness of the image processing techniques applied to the data collected from various visual sensors. Therefore, it is essential to develop the capability to detect objects like vehicles and pedestrians under challenging conditions such as like unpleasant weather. Ensembling multiple baseline deep learning models under different voting strategies for object detection and utilizing data augmentation to boost the models' performance is proposed to solve this problem. The data augmentation technique is particularly useful and works with limited training data for OD applications. Furthermore, using the baseline models significantly speeds up the OD process as compared to the custom models due to transfer learning. Therefore, the ensembling approach can be highly effective in resource-constrained devices deployed for autonomous vehicles in uncertain weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and were able to identify objects from the images captured in the adverse foggy and rainy weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and reached 32.75% mean average precision (mAP) and 52.56% average precision (AP) in detecting cars in the adverse fog and rain weather conditions present in the dataset. The effectiveness of multiple voting strategies for bounding box predictions on the dataset is also demonstrated. These strategies help increase the explainability of object detection in autonomous systems and improve the performance of the ensemble techniques over the baseline models.

Dataset Information

DATS_2022: A versatile indian dataset for object detection in unstructured traffic conditions

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets