Deep Learning based Object Detection Model for Autonomous Driving Research using CARLA Simulator

Niranjan, D.R.; VinayKarthik, BC; Mohana,

doi:10.1109/icosec51865.2021.9591747

Cited by 29 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Carla (car learning to act) (Niranjan, VinayKarthik, et al 2021) is a high-fidelity open source simulator for autonomous driving research (Dosovitskiy et al 2017b). It provides a realistic urban environment with a variety of roads, buildings, vehicles, and pedestrians.…”

Section: Carla Simulatormentioning

confidence: 99%

“…We categorize fog density into five distinct levels: 25%, 50%, 75%, and 100%. Leveraging the Carla simulator (Car Learning to Act) (Dosovitskiy et al 2017b;Niranjan, VinayKarthik, et al 2021), we generate a comprehensive dataset encompassing a diverse range of fog densities . Subsequently, we implement a bounding box-based machine learning algorithm to effectively detect objects under varying fog conditions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving the Perception of Objects under Foggy Conditions in the Surrounding Environment

Chaar,

Raiyn,

Weidl

2024

Preprint

View full text Add to dashboard Cite

Autonomous Driving (AD) technology has rapidly advanced in recent years. Some challenges remain, particularly in ensuring robust performance under adverse weather conditions, like heavy fog. To address this, we propose a multi-class fog density classification approach to enhance the performance of AD systems. By dividing the fog density into multiple classes (25\%, 50\%, 75\%, and 100\%) and generating separate data-sets for each class using the Carla simulator, we can independently improve perception for each fog density and examine the effects of fog at each level. This approach offers several advantages, including improved perception, targeted training, and enhanced generalizability. The results show improved perception of objects from the categories: cars, buses, trucks, vans, pedestrians, and traffic lights. Our multi-class fog density approach is a promising step towards achieving robust AD system performance under adverse weather conditions.

show abstract

Section: Carla Simulatormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving the Perception of Objects under Foggy Conditions in the Surrounding Environment

Chaar,

Raiyn,

Weidl

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…General object detection algorithms have been widely used in many fields, such as autonomous driving, smart healthcare, and industrial detection [13][14][15]. Among them, the YOLO algorithm series, as an outstanding representative of single-stage object detection algorithms, significantly optimizes the real-time performance of object detection by integrating the process of feature extraction and classification into a single neural network.…”

Section: Yolo Series Algorithmsmentioning

confidence: 99%

MACNet: A More Accurate and Convenient Pest Detection Network

Hu,

Wang,

Wang

et al. 2024

Electronics

View full text Add to dashboard Cite

Pest detection: This process is essential for the early warning of pests in the agricultural sector. However, the challenges posed by agricultural pest datasets include but are not limited to species diversity, small individuals, high concentration, and high similarity, which greatly increase the difficulty of pest detection and control. To effectively solve these problems, this paper proposes an innovative object detection model named MACNet. MACNet is optimized based on YOLOv8s, introducing a content-based feature sampling strategy to obtain richer object feature information, and adopts distribution shifting convolution technology, which not only improves the accuracy of detection but also successfully reduces the size of the model, making it more suitable for deployment in the actual environment. Finally, our test results on the Pest24 dataset verify the good performance of MACNet; its detection accuracy reaches 43.1 AP which is 0.5 AP higher than that of YOLOv8s, and the computational effort is reduced by about 30%. This achievement not only demonstrates the efficiency of MACNet in agricultural pest detection, but also further confirms the great potential and practical value of deep learning technology in complex application scenarios.

show abstract

“…But the predetermined model is not fit to resolve the difficulty of algorithm called scaling problem which remains unchanged and causes the result of pedestrian detection method. The conventional method has been handled to resolve the scaling problem on the two-dimensional scale [7]. Firstly, brute-force data is increased for improving the capacity of scale-invariance method.…”

Section: Introductionmentioning

confidence: 99%

Segmentation Based Real Time Anomaly Detection and Tracking Model for Pedestrian Walkways

Chitra¹

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Presently, video surveillance is commonly employed to ensure security in public places such as traffic signals, malls, railway stations, etc. A major challenge in video surveillance is the identification of anomalies that exist in it such as crimes, thefts, and so on. Besides, the anomaly detection in pedestrian walkways has gained significant attention among the computer vision communities to enhance pedestrian safety. The recent advances of Deep Learning (DL) models have received considerable attention in different processes such as object detection, image classification, etc. In this aspect, this article designs a new Panoptic Feature Pyramid Network based Anomaly Detection and Tracking (PFPN-ADT) model for pedestrian walkways. The proposed model majorly aims to the recognition and classification of different anomalies present in the pedestrian walkway like vehicles, skaters, etc. The proposed model involves panoptic segmentation model, called Panoptic Feature Pyramid Network (PFPN) is employed for the object recognition process. For object classification, Compact Bat Algorithm (CBA) with Stacked Auto Encoder (SAE) is applied for the classification of recognized objects. For ensuring the enhanced results better anomaly detection performance of the PFPN-ADT technique, a comparison study is made using University of California San Diego (UCSD) Anomaly data and other benchmark datasets (such as Cityscapes, ADE20K, COCO), and the outcomes are compared with the Mask Recurrent Convolutional Neural Network (RCNN) and Faster Convolutional Neural Network (CNN) models. The simulation outcome demonstrated the enhanced performance of the PFPN-ADT technique over the other methods.

show abstract

Deep Learning based Object Detection Model for Autonomous Driving Research using CARLA Simulator

Cited by 29 publications

References 26 publications

Improving the Perception of Objects under Foggy Conditions in the Surrounding Environment

Improving the Perception of Objects under Foggy Conditions in the Surrounding Environment

MACNet: A More Accurate and Convenient Pest Detection Network

Segmentation Based Real Time Anomaly Detection and Tracking Model for Pedestrian Walkways

Contact Info

Product

Resources

About