An Algorithm for Obstacle Detection based on YOLO and Light Filed Camera

Zhang, Rumin; Yang, Yifeng; Wang, Wenyi; Zeng, Liaoyuan; Chen, Jianwen; McGrath, Sean

doi:10.1109/icsenst.2018.8603600

Cited by 25 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2. Darknet-53 architecture [16] In a single-stage object detection network, there are much interesting research and its applications: Detecting obstacles with the light field camera was proposed by [29]. YOLO, deep learning was used to classify objects in the image under the indoor environment into categories.…”

Section: Literature Review and Related Workmentioning

confidence: 99%

An assistive model of obstacle detection based on deep learning: YOLOv3 for visually impaired people

Rachburee

Punlumjeak

2021

IJECE

View full text Add to dashboard Cite

The World Health Organization (WHO) reported in 2019 that at least 2.2 billion people were visual-impairment or blindness. The main problem of living for visually impaired people have been facing difficulties in moving even indoor or outdoor situations. Therefore, their lives are not safe and harmful. In this paper, we proposed an assistive application model based on deep learning: YOLOv3 with a Darknet-53 base network for visually impaired people on a smartphone. The Pascal VOC2007 and Pascal VOC2012 were used for the training set and used Pascal VOC2007 test set for validation. The assistive model was installed on a smartphone with an eSpeak synthesizer which generates the audio output to the user. The experimental result showed a high speed and also high detection accuracy. The proposed application with the help of technology will be an effective way to assist visually impaired people to interact with the surrounding environment in their daily life.

show abstract

Section: Literature Review and Related Workmentioning

confidence: 99%

An assistive model of obstacle detection based on deep learning: YOLOv3 for visually impaired people

Rachburee

Punlumjeak

2021

IJECE

View full text Add to dashboard Cite

show abstract

“…The system is composed of three main components, which includes the Controller, Base Station and the Metasurface reflector. Two cameras (top and side view) feed images to the Controller server, which contains an online image processing module known as You Only Look Once (YOLO) machine learning algorithm [20]. This algorithm is used to detect the obstacles and identify the object's profile (its position and dimensions) using a monochromatic image of the obstacle.…”

Section: Indoor Thzpf Management Systemmentioning

confidence: 99%

“…However, we need to extend (20) to incorporate 1) the partial loss of signal strength due to absorption of an indoor obstacle, 2) the partial loss of signal strength from each reflection of the metasurface reflector. In our scenarios, we assume a group of signal reflections, and the new SNR for each signal is defined as…”

Section: Terahertz Receiver Power Modelmentioning

confidence: 99%

Digital Twin for Metasurface Reflector Management in 6G Terahertz Communications

et al. 2020

View full text Add to dashboard Cite

The performance demands from data-intensive applications, such as multimedia streaming, as well as the growing number of devices connecting to the Internet, will increase the need for higher capacity wireless communication links. The research community has recently explored regions of the spectrum, including the Terahertz band (0.1 THz to 10 THz), that are underutilised for communications. THz frequencies come with a plethora of special challenges, one of which is the very narrow effective beam, thereby requiring a Line of Sight (LoS) between sender and receiver. Researchers have explored the use of reflectors that can redirect beams around blockages. In this paper, we propose a THz signal guidance system where a Digital Twin is used to model, predict and control the signal propagation characteristics of an indoor space. Our approach finds the best THz signal path from the base station to the mobile target via the tunable metamaterial walls, avoiding obstacles as needed, using geometric (ray tracing), path loss and Terahertz Potential Field (THzPF) models. With this knowledge, the digital twin guides the selection of antenna strips at a base station and the reflectors along the signal path. A top-view camera, with advanced image processing, provides context updates (obstacle and mobile target locations) to the digital twin. The image processing system also senses factors like water vapour concentration, and the material composition and surface roughness of obstacles. Such factors affect propagation strength, and the digital twin modifies the beam paths to adapt. Simulation results have shown the efficiency of our control system to maintain a reliable signal connection while minimising the use of antenna and reflector strips. Our system is the first proposal that maximises THz signal-to-noise ratio (SNR) through such a dynamic and robust control system, which integrates image processing of a room with base station configuration.

show abstract

“…Rumin Zhang et al [9] proposed an algorithm that combines the YOLO object detection algorithm and the light field camera which is simpler than normal RGB-D sensor and acquires depth image and high-resolution images at the same in one exposure. The RGB Image rendered by the light field camera is taken as an input of the YOLO model which was trained base on nearly 100 categories of common objects.…”

Section: Related Workmentioning

confidence: 99%

An Intelligent Rider Assistance System Using Machine L earning for Two Wheel Vehicles

John*,

R L

2019

IJEAT

View full text Add to dashboard Cite

As far as a rider is concerned, safety is the first priority while driving a vehicle. There have been significant changes over the years in the design of four wheeler in terms of security. During the design of vehicles manufacturers are incorporating many modifications to the existing model so that the security is more. But when the safety of motorbikes is concerned this is not true, as there exits some blind spots which are not visible to the rider through the mirrors. Blind spots are the rare quarter areas towards the rear of the vehicle on both sides, vehicles in the contiguous paths of the road may fall into these vulnerable sides and driver may not be able to see them using only the mirrors. In this paper we have introduced a new approach using machine learning tools to detect the obstacles and to alert rider and there by reducing the risk of collision. This system could reduce significant amount of risk that the rider is going to face because of the obstacles which are not visible through the mirrors.

show abstract

An Algorithm for Obstacle Detection based on YOLO and Light Filed Camera

Cited by 25 publications

References 7 publications

An assistive model of obstacle detection based on deep learning: YOLOv3 for visually impaired people

An assistive model of obstacle detection based on deep learning: YOLOv3 for visually impaired people

Digital Twin for Metasurface Reflector Management in 6G Terahertz Communications

An Intelligent Rider Assistance System Using Machine L earning for Two Wheel Vehicles

Contact Info

Product

Resources

About