360&amp;#x00B0; Detection and tracking algorithm of both pedestrian and vehicle using fisheye images

Bertozzi, Massimo; Castangia, Luca; Cattani, Silvia; Prioletti, Antonio; Versari, Pietro

doi:10.1109/ivs.2015.7225675

Cited by 57 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others include stereo camera-based approaches to make use of the additional depth information available [3]. Bertozzi et al [4] use images from 4 fisheye cameras to detect and Another approach is to combine the data from various sensors to arrive at a more accurate estimate. This sensor fusion-based approach has also been explored for Carnegie Mellon University's autonomous driving research vehicle [1] [5].…”

Section: A Related Workmentioning

confidence: 99%

Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images

Baek

Davies

Geng

et al. 2018

2018 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

The ability to detect pedestrians and other moving objects is crucial for an autonomous vehicle. This must be done in real-time with minimum system overhead. This paper discusses the implementation of a surround view system to identify moving as well as static objects that are close to the ego vehicle. The algorithm works on 4 views captured by fisheye cameras which are merged into a single frame. The moving object detection and tracking solution uses minimal system overhead to isolate regions of interest (ROIs) containing moving objects. These ROIs are then analyzed using a deep neural network (DNN) to categorize the moving object. With deployment and testing on a real car in urban environments, we have demonstrated the practical feasibility of the solution 1 .

show abstract

Section: A Related Workmentioning

confidence: 99%

Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images

Baek

Davies

Geng

et al. 2018

2018 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

show abstract

“…Hence, a process called image unwarping is necessary to correct severe distortion of the images produced by the wideangle lens. Image unwarping is used for obtaining a wide-angle view without strong aberration by both correcting lens distortion [11]. In order to exploit the large field of view of wide-angle lenses by correcting the lens distortion, this study adapted an unwarping approach proposed in Schulz et al [12].…”

Section: Unwarpingmentioning

confidence: 99%

Detection of Nearby Obstacles with Monocular Vision for Earthmoving Operations

Son¹,

Sung²,

Choi³

et al. 2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

The equipment used in earthmoving operations poses a significant threat to the safety of the equipment operator and construction workers due to the operator's inherently poor visibility of the surrounding environment. This study proposes a method of automated detection of nearby obstacles with monocular vision, with the goal of protecting the equipment operator and construction workers from potentially dangerous situations, such as collisions between earthmoving equipment and obstacles within a certain proximity. The proposed method consists of three steps: 1) correction of lens distortion prior to further processing, 2) shadow removal, and 3) detection of nearby obstacles with a predefined height level via perspective transformations. The proposed method was tested on video streams acquired from a camera installed on the side of the equipment body while an excavator executed excavating and moving tasks. The experimental results showed that the proposed method can provide the equipment operator with information about nearby obstacles during the excavator's manipulation and transportation. It is expected that the proposed method can be implemented in rearview monitoring systems and surrounding view monitoring systems for operator assistance and to achieve active safety.

show abstract

“…Due to the wide availability of consumer-level panoramic video capturing and imaging devices, panoramic images are widely used in many fields [1][2][3][4][5][6]. For example, they are used in 360-degree object tracking [1,4], equirectangular super-resolution [3], privacy protection in Google Street View [5] and roadway inventory management about traffic signs [6]. Object detection based on panoramic images is one of the key technologies to make panoramic images widely applied.…”

Section: Introductionmentioning

confidence: 99%

Pano-RSOD: A Dataset and Benchmark for Panoramic Road Scene Object Detection

Tong

Gao

et al. 2019

Electronics

View full text Add to dashboard Cite

Panoramic images have a wide range of applications in many fields with their ability to perceive all-round information. Object detection based on panoramic images has certain advantages in terms of environment perception due to the characteristics of panoramic images, e.g., lager perspective. In recent years, deep learning methods have achieved remarkable results in image classification and object detection. Their performance depends on the large amount of training data. Therefore, a good training dataset is a prerequisite for the methods to achieve better recognition results. Then, we construct a benchmark named Pano-RSOD for panoramic road scene object detection. Pano-RSOD contains vehicles, pedestrians, traffic signs and guiding arrows. The objects of Pano-RSOD are labelled by bounding boxes in the images. Different from traditional object detection datasets, Pano-RSOD contains more objects in a panoramic image, and the high-resolution images have 360-degree environmental perception, more annotations, more small objects and diverse road scenes. The state-of-the-art deep learning algorithms are trained on Pano-RSOD for object detection, which demonstrates that Pano-RSOD is a useful benchmark, and it provides a better panoramic image training dataset for object detection tasks, especially for small and deformed objects.

show abstract

360° Detection and tracking algorithm of both pedestrian and vehicle using fisheye images

Cited by 57 publications

References 17 publications

Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images

Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images

Detection of Nearby Obstacles with Monocular Vision for Earthmoving Operations

Pano-RSOD: A Dataset and Benchmark for Panoramic Road Scene Object Detection

Contact Info

Product

Resources

About