Real-Time Traffic Light Detection with Frequency Patterns Using a High-Speed Camera

LEDs are widely employed as traffic lights. Because most LED traffic lights are driven by alternative power, they blink at high frequencies, even at twice their frequencies. We propose a method to detect a traffic light from images captured by a high-speed camera that can recognize a blinking traffic light. This technique is robust under various illuminations because it can detect traffic lights by extracting information from the blinking pixels at a specific frequency. The method is composed of six modules, which includes a band-pass filter and a Kalman filter. All the modules run simultaneously to achieve real-time processing and can run at 500 fps for images with a resolution of 800 × 600. This technique was verified on an original dataset captured by a high-speed camera under different illumination conditions such as a sunset or night scene. The recall and accuracy justify the generalization of the proposed detection system. In particular, it can detect traffic lights with a different appearance without tuning parameters and without datasets having to be learned.

Download Full-text

High-speed camera with real time processing for frequency domain imaging

Biomedical Optics Express ◽

10.1364/boe.2.001931 ◽

2011 ◽

Vol 2 (7) ◽

pp. 1931 ◽

Cited By ~ 3

Author(s):

Victor Shia ◽

David Watt ◽

Gregory W. Faris

Keyword(s):

Frequency Domain ◽

Real Time ◽

High Speed ◽

High Speed Camera ◽

Real Time Processing ◽

Time Processing

Download Full-text

Rapid Foreign Object Detection System on Seaweed Using VNIR Hyperspectral Imaging

Sensors ◽

10.3390/s21165279 ◽

2021 ◽

Vol 21 (16) ◽

pp. 5279

Author(s):

Dong-Hoon Kwak ◽

Guk-Jin Son ◽

Mi-Kyung Park ◽

Young-Duk Kim

Keyword(s):

Object Detection ◽

Real Time ◽

Hyperspectral Imaging ◽

High Speed ◽

Detection System ◽

Imaging Techniques ◽

Foreign Object ◽

Subtraction Method ◽

Foreign Objects ◽

Time Operation

The consumption of seaweed is increasing year by year worldwide. Therefore, the foreign object inspection of seaweed is becoming increasingly important. Seaweed is mixed with various materials such as laver and sargassum fusiforme. So it has various colors even in the same seaweed. In addition, the surface is uneven and greasy, causing diffuse reflections frequently. For these reasons, it is difficult to detect foreign objects in seaweed, so the accuracy of conventional foreign object detectors used in real manufacturing sites is less than 80%. Supporting real-time inspection should also be considered when inspecting foreign objects. Since seaweed requires mass production, rapid inspection is essential. However, hyperspectral imaging techniques are generally not suitable for high-speed inspection. In this study, we overcome this limitation by using dimensionality reduction and using simplified operations. For accuracy improvement, the proposed algorithm is carried out in 2 stages. Firstly, the subtraction method is used to clearly distinguish seaweed and conveyor belts, and also detect some relatively easy to detect foreign objects. Secondly, a standardization inspection is performed based on the result of the subtraction method. During this process, the proposed scheme adopts simplified and burdenless calculations such as subtraction, division, and one-by-one matching, which achieves both accuracy and low latency performance. In the experiment to evaluate the performance, 60 normal seaweeds and 60 seaweeds containing foreign objects were used, and the accuracy of the proposed algorithm is 95%. Finally, by implementing the proposed algorithm as a foreign object detection platform, it was confirmed that real-time operation in rapid inspection was possible, and the possibility of deployment in real manufacturing sites was confirmed.

Download Full-text

A POINT-BASED ASYNCHRONOUS REMOTE VISUALIZATION FRAMEWORK FOR REAL-TIME VIRTUAL REALITY

International Journal of Image and Graphics ◽

10.1142/s0219467808003040 ◽

2008 ◽

Vol 08 (02) ◽

pp. 189-207

Author(s):

JINGHUA GE ◽

DANIEL J. SANDIN ◽

TOM PETERKA ◽

ROBERT KOOIMA ◽

JAVIER I. GIRADO ◽

...

Keyword(s):

Virtual Reality ◽

Real Time ◽

High Speed ◽

Large Scale ◽

Julia Set ◽

Remote Visualization ◽

Space Partition ◽

Original Dataset ◽

View Reconstruction ◽

Occlusion Culling

High speed interactive virtual reality (VR) exploration of scientific datasets is a challenge when the visualization is computationally expensive. This paper presents a point-based remote visualization pipeline for real-time virtual reality (VR) with asynchronous client-server coupling. Steered by the client-end frustum request, the remote server samples the original dataset into 3D point samples and sends them back to the client for view updating. From every view updating frame, the client incrementally builds up a point-based geometry under an octree-based space partition hierarchy. At every view-reconstruction frame, the client continuously splats the available points onto the screen with efficient occlusion culling and view-dependent level of detail (LOD) control. An experimental visualization framework with a server-end computer cluster and a client-end head-tracked autostereo VR desktop display is used to visualize large-scale mesh datasets and ray-traced 4D Julia set datasets. The overall performance of the VR view reconstruction is about 15 fps and independent of the original dataset complexity.

Download Full-text

Preparation of Nickel Nanoparticles by Direct Current Arc Discharge Method and Their Catalytic Application in Hybrid Na-Air Battery

Nanomaterials ◽

10.3390/nano8090684 ◽

2018 ◽

Vol 8 (9) ◽

pp. 684 ◽

Cited By ~ 9

Author(s):

Fengmei Su ◽

Xuechao Qiu ◽

Feng Liang ◽

Manabu Tanaka ◽

Tao Qu ◽

...

Keyword(s):

Direct Current ◽

Composite Structures ◽

High Speed ◽

Large Scale ◽

Nickel Nanoparticles ◽

Arc Discharge ◽

Band Pass Filter ◽

Pass Filter ◽

Air Battery ◽

Discharge Method

Nickel nanoparticles were prepared by the arc discharge method. Argon and argon/hydrogen mixtures were used as plasma gas; the evaporation of anode material chiefly resulted in the formation of different arc-anode attachments at different hydrogen concentrations. The concentration of hydrogen was fixed at 0, 30, and 50 vol% in argon arc, corresponding to diffuse, multiple, and constricted arc-anode attachments, respectively, which were observed by using a high-speed camera. The images of the cathode and anode jets were observed with a suitable band-pass filter. The relationship between the area change of the cathode/anode jet and the synchronous voltage/current waveform was studied. By investigating diverse arc-anode attachments, the effect of hydrogen concentration on the features of nickel nanoparticles were investigated, finding that 50 vol% H2 concentration has high productivity, fine crystallinity, and appropriate size distribution. The synthesized nickel nanoparticles were then used as catalysts in a hybrid sodium–air battery. Compared with commercial a silver nanoparticle catalyst and carbon black, nickel nanoparticles have better electrocatalytic performance. The promising electrocatalytic activity of nickel nanoparticles can be ascribed to their good crystallinity, effective activation sites, and Ni/NiO composite structures. Nickel nanoparticles prepared by the direct current (DC) arc discharge method have the potential to be applied as catalysts on a large scale.

Download Full-text

Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights

Sensors ◽

10.3390/s20216218 ◽

2020 ◽

Vol 20 (21) ◽

pp. 6218

Author(s):

Rodrigo Carvalho Barbosa ◽

Muhammad Shoaib Ayub ◽

Renata Lopes Rosa ◽

Demóstenes Zegarra Rodríguez ◽

Lunchakorn Wuttisittikulkij

Keyword(s):

Deep Learning ◽

Traffic Control ◽

Detection System ◽

Lightweight Design ◽

Vehicle Detection ◽

Activation Function ◽

Urban Traffic ◽

Vehicle Classification ◽

Traffic Light ◽

Traffic Lights

Minimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of priority vehicle classification algorithms with high accuracy, fast processing, and a lightweight solution. For filling those gaps, a vehicle detection system is proposed, which is integrated with an intelligent traffic light. Thus, this work proposes (1) a novel vehicle detection model named Priority Vehicle Image Detection Network (PVIDNet), based on YOLOV3, (2) a lightweight design strategy for the PVIDNet model using an activation function to decrease the execution time of the proposed model, (3) a traffic control algorithm based on the Brazilian Traffic Code, and (4) a database containing Brazilian vehicle images. The effectiveness of the proposed solutions were evaluated using the Simulation of Urban MObility (SUMO) tool. Results show that PVIDNet reached an accuracy higher than 0.95, and the waiting time of priority vehicles was reduced by up to 50%, demonstrating the effectiveness of the proposed solution.

Download Full-text

Real-time monitoring of laser scribing process utilizing high-speed camera

International Congress on Applications of Lasers & Electro-Optics ◽

10.2351/1.5118570 ◽

2016 ◽

Author(s):

Hamid Roozbahani ◽

Antti Salminen ◽

Matti Manninen

Keyword(s):

Real Time ◽

High Speed ◽

High Speed Camera ◽

Real Time Monitoring ◽

Laser Scribing

Download Full-text

Design and Implementation of a High-Speed Real-Time Position Detection System in Electromagnetic Coil Launcher

IEEE Transactions on Plasma Science ◽

10.1109/tps.2020.3019045 ◽

2020 ◽

Vol 48 (9) ◽

pp. 3203-3210

Author(s):

Guan Xiao Cun ◽

Shuai Wang ◽

Denghua Guo ◽

Shaohua Guan ◽

Baolong Liu ◽

...

Keyword(s):

Real Time ◽

High Speed ◽

Detection System ◽

Electromagnetic Coil ◽

Design And Implementation ◽

Position Detection ◽

Time Position

Download Full-text

Researching the Information of Transmission Technology Based on Traffic Lights

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.644-650.4538 ◽

2014 ◽

Vol 644-650 ◽

pp. 4538-4541

Author(s):

Qiang Li ◽

Xin Rui Zhang

Keyword(s):

Visible Light ◽

Image Recognition ◽

Communication Technology ◽

High Speed ◽

Visible Light Communication ◽

Qr Code ◽

Visible Light Communications ◽

Traffic Light ◽

Traffic Lights ◽

Very High

This design is based on Visible Light Communication Technology, to achieve outdoor visible light communications and image recognition etc. through traffic lights. It will play a role on promoting the utilization of traffic lights. The system uses a LED dot matrix to imitate the traffic light, loading QR Code information on the LED dot matrix and then transporting it in a very high-speed flashing. In receiving terminal, first, webcam OV7670 collects information which from the LED dot matrix, then conveys the picture to FPGA, which is the processor. FPGA will handle the picture by gray scale processing, medium filtering and binary processing at last. Thus, the picture from the LED dot matrix will change to ‘0’ and ‘1’ in binary area. Secondly, as there’s a relationship between LED dot matrix and webcam pixels, we can count how many pixels represent one LED. Finally, we can decode the QR Code based on its own style, and display the final result on the TFT screen.

Download Full-text