Hybrid LED traffic light detection using high-speed camera

2016 ◽  
Author(s):  
Zhipeng Wu ◽  
Yoshihiro Watanabe ◽  
Masatoshi Ishikawa
Keyword(s):  
High Speed ◽  
High Speed Camera ◽  
Traffic Light ◽  
Light Detection

LED Traffic Light Detection Using High-speed-camera Image Processing for Visible Light Communication

2011 ◽  
Vol 65 (3) ◽  
pp. 354-360 ◽  
Author(s):  
H. Chinthaka N. Premachandra ◽  
Tomohiro Yendo ◽  
Mehrdad Panahpour Tehrani ◽  
Takaya Yamazato ◽  
Hiraku Okada ◽  
...  
Keyword(s):  
Image Processing ◽  
Visible Light ◽  
High Speed ◽  
Visible Light Communication ◽  
High Speed Camera ◽  
Traffic Light ◽  
Light Detection ◽  
Camera Image

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

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 4035 ◽  
Author(s):  
Kento Yabuuchi ◽  
Masahiro Hirano ◽  
Taku Senoo ◽  
Norimasa Kishi ◽  
Masatoshi Ishikawa
Keyword(s):  
Real Time ◽  
High Speed ◽  
Detection System ◽  
Band Pass Filter ◽  
High Speed Camera ◽  
Traffic Light ◽  
Pass Filter ◽  
Real Time Processing ◽  
Traffic Lights ◽  
Original Dataset

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.

HSI COLOR CONVERSION AND HOG FEATURE EXTRACTION IN TRAFFIC LIGHT DETECTION USING AdaBSF

2017 ◽  
Vol 5 (3) ◽  
pp. 20
Author(s):  
JEBISHA J ◽  
MONISHA V ◽  
JEMI B. FEMILA ◽  
◽  
◽  
...  
Keyword(s):  
Feature Extraction ◽  
Traffic Light ◽  
Light Detection ◽  
Color Conversion

scholarly journals Tracking by Deblatting

2021 ◽  
Author(s):  
Denys Rozumnyi ◽  
Jan Kotera ◽  
Filip Šroubek ◽  
Jiří Matas
Keyword(s):  
High Speed ◽  
High Performance ◽  
Motion Blur ◽  
Velocity Estimation ◽  
High Speed Camera ◽  
Trajectory Function ◽  
Novel Approach ◽  
Blind Deblurring ◽  
Object Trajectories ◽  
Complex Trajectories

AbstractObjects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects travel a considerable distance during exposure time of a single frame, and therefore, their position in the frame is not well defined. They appear as semi-transparent streaks due to the motion blur and cannot be reliably tracked by general trackers. We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. By postprocessing, non-causal Tracking by Deblatting estimates continuous, complete, and accurate object trajectories for the whole sequence. Tracked objects are precisely localized with higher temporal resolution than by conventional trackers. Energy minimization by dynamic programming is used to detect abrupt changes of motion, called bounces. High-order polynomials are then fitted to smooth trajectory segments between bounces. The output is a continuous trajectory function that assigns location for every real-valued time stamp from zero to the number of frames. The proposed algorithm was evaluated on a newly created dataset of videos from a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms the baselines both in recall and trajectory accuracy. Additionally, we show that from the trajectory function precise physical calculations are possible, such as radius, gravity, and sub-frame object velocity. Velocity estimation is compared to the high-speed camera measurements and radars. Results show high performance of the proposed method in terms of Trajectory-IoU, recall, and velocity estimation.

Influence of Main Swirler Vane Angle on the Ignition Performance of TeLESS-II Combustor

2016 ◽  
Vol 139 (1) ◽  
Author(s):  
Bo Wang ◽  
Chi Zhang ◽  
Yuzhen Lin ◽  
Xin Hui ◽  
Jibao Li
Keyword(s):  
High Speed ◽  
Inlet Temperature ◽  
Main Stage ◽  
Ignition Process ◽  
High Speed Camera ◽  
Fuel Distribution ◽  
Fuel Droplets ◽  
Planar Laser ◽  
Cfd Method ◽  
Vane Angle

In order to balance the low emission and wide stabilization for lean premixed prevaporized (LPP) combustion, the centrally staged layout is preferred in advanced aero-engine combustors. However, compared with the conventional combustor, it is more difficult for the centrally staged combustor to light up as the main stage air layer will prevent the pilot fuel droplets arriving at igniter tip. The goal of the present paper is to study the effect of the main stage air on the ignition of the centrally staged combustor. Two cases of the main swirler vane angle of the TeLESS-II combustor, 20 deg and 30 deg are researched. The ignition results at room inlet temperature and pressure show that the ignition performance of the 30 deg vane angle case is better than that of the 20 deg vane angle case. High-speed camera, planar laser induced fluorescence (PLIF), and computational fluids dynamics (CFD) are used to better understand the ignition results. The high-speed camera has recorded the ignition process, indicated that an initial kernel forms just adjacent the liner wall after the igniter is turned on, the kernel propagates along the radial direction to the combustor center and begins to grow into a big flame, and then it spreads to the exit of the pilot stage, and eventually stabilizes the flame. CFD of the cold flow field coupled with spray field is conducted. A verification of the CFD method has been applied with PLIF measurement, and the simulation results can qualitatively represent the experimental data in terms of fuel distribution. The CFD results show that the radial dimensions of the primary recirculation zone of the two cases are very similar, and the dominant cause of the different ignition results is the vapor distribution of the fuel. The concentration of kerosene vapor of the 30 deg vane angle case is much larger than that of the 20 deg vane angle case close to the igniter tip and along the propagation route of the kernel, therefore, the 30 deg vane angle case has a better ignition performance. For the consideration of the ignition performance, a larger main swirler vane angle of 30 deg is suggested for the better fuel distribution when designing a centrally staged combustor.

Sign in / Sign up

Export Citation Format

Share Document