Learning Framework for Robust Obstacle Detection, Recognition, and Tracking

Nguyen, Vinh Dinh; Nguyen, Hau Van; Tran, Dinh Thi; Lee, Sang Jun; Jeon, Jae Wook

doi:10.1109/tits.2016.2614818

Cited by 45 publications

(25 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also many deep learning approaches available for obstacle detection and tracking. In [13], one such approach is discussed which uses multiple sources of local patterns and depth information to yield robust on-road vehicle and pedestrian detection, recognition, and tracking. [14] discusses obstacle detection and classification using deep learning for tracking in high-speed autonomous driving.…”

Section: Deep Learning-based Approachmentioning

confidence: 99%

Obstacle Detection and Track Detection in Autonomous Cars

Iqbal¹

2020

Autonomous Vehicle and Smart Traffic

View full text Add to dashboard Cite

This chapter illustrates the history and recent advancements in the field of Autonomous Vehicles with regard to two important concerns that play the most vital role in successful implementation and working of an Autonomous Car: (1) Obstacle Detection and (2) Track Detection. The car should be able to detect the obstacles for smooth and efficient working in order to avoid accident and collision. It should also be able to calculate the distance of the obstacle from the car. Similarly, Track Detection is also important as the autonomous car should stay within a predefined track and has to keep itself within the yellow lines on both sides of the road. This chapter elaborates the technologies and advancements that have been presented in the literature till date that deal with Obstacle Detection and Track Detection in Autonomous Cars/Vehicles.

show abstract

Section: Deep Learning-based Approachmentioning

confidence: 99%

Obstacle Detection and Track Detection in Autonomous Cars

Iqbal¹

2020

Autonomous Vehicle and Smart Traffic

View full text Add to dashboard Cite

show abstract

“…Approach includes unsupervised training to help learn and modulate weights based on wide range of training data. Obstacle validation algorithms are included to reduce the count of valid detections [1]. Concepts like Optical flow and Histogram of magnitudes is used to analyze motion of objects, which are not evident to bare eyes.…”

Section: Literature Surveymentioning

confidence: 99%

Object Detection and Tracking using Deep Learning and Artificial Intelligence for Video Surveillance Applications

Mohana¹,

Aradhya²

2019

IJACSA

View full text Add to dashboard Cite

Data is the new oil in current technological society. The impact of efficient data has changed benchmarks of performance in terms of speed and accuracy. The enhancement is visualizable because the processing of data is performed by two buzzwords in industry called Computer Vision (CV) and Artificial Intelligence (AI). Two technologies have empowered major tasks such as object detection and tracking for traffic vigilance systems. As the features in image increases demand for efficient algorithm to excavate hidden features increases. Convolution Neural Network (CNN) model is designed for urban vehicle dataset for single object detection and YOLOv3 for multiple object detection on KITTI and COCO dataset. Model performance is analyzed, evaluated and tabulated using performance metrics such as True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), Accuracy, Precision, confusion matrix and mean Average Precession (mAP). Objects are tracked across the frames using YOLOv3 and Simple Online Real Time Tracking (SORT) on traffic surveillance video. This paper upholds the uniqueness of the state of the art networks like DarkNet. The efficient detection and tracking on urban vehicle dataset is witnessed. The algorithms give real-time, accurate, precise identifications suitable for realtime traffic applications.

show abstract

“…They combine convolutional neural networks and conditional random fields for reliable segmentation. Nguyen et al [22] proposed an obstacle detection, recognition, and tracking algorithm using stereo disparity and deep neural networks. Although deep architecture based detection algorithms achieve high detection accuracy, they require a high performance graphics processing unit (GPU) platform for learning and prediction.…”

Section: Related Workmentioning

confidence: 99%

Fast Obstacle Detection for Monocular Autonomous Mobile Robots

Kaneko

Yoshida

Kim

2017

SICE Journal of Control, Measurement, and System Integration

View full text Add to dashboard Cite

: This paper proposes a monocular vision based obstacle detection algorithm for autonomous mobile robots. Our main algorithm consists of two stages. In the first stage, we use an inverse perspective mapping (IPM) based method for detecting small portions of an obstacle in the input image. In the second stage, we perform image abstraction and geodesic distance computation for segmenting the obstacle. We use the simple linear iterative clustering (SLIC) superpixel algorithm for decomposing the image into basic elements that preserve relevant structure, but abstract undesirable detail. The source superpixel for geodesic distance computation is selected according to semi-local texture features. Then we compute the obstacle score for accurate segmentation. Experimental results have shown that our proposed method achieves accuracy comparable to the state-of-the-art method, with more than 7 times faster computation.

show abstract

Learning Framework for Robust Obstacle Detection, Recognition, and Tracking

Cited by 45 publications

References 28 publications

Obstacle Detection and Track Detection in Autonomous Cars

Obstacle Detection and Track Detection in Autonomous Cars

Object Detection and Tracking using Deep Learning and Artificial Intelligence for Video Surveillance Applications

Fast Obstacle Detection for Monocular Autonomous Mobile Robots

Contact Info

Product

Resources

About