Vehicles detection based on extremas in nighttime driving scene

Ogura, Ryota; Ohashi, Gosuke

doi:10.1109/gcce.2012.6379950

Cited by 10 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Mobile detection: performed when a rear-facing camera is mounted on the back or the front of a moving vehicle [37], [38], [39], [40]. Detection from a mobile platform is inherently more challenging, since-unlike with static camera imagesstreetlights and other potential sources of false-positive information cannot be readily filtered out and the detection area cannot be manually defined [33].…”

Section: A Survey Of State-of-the-art Researchmentioning

confidence: 99%

See 1 more Smart Citation

Robust and Computationally Lightweight Autonomous Tracking of Vehicle Taillights and Signal Detection by Embedded Smart Cameras

Almagambetov

Velipasalar

Casares

2015

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

An important aspect of collision avoidance and driver assistance systems, as well as autonomous vehicles, is the tracking of vehicle taillights and the detection of alert signals (turns and brakes). In this paper, we present the design and implementation of a robust and computationally lightweight algorithm for a real-time vision system, capable of detecting and tracking vehicle taillights, recognizing common alert signals using a vehicle-mounted embedded smart camera, and counting the cars passing on both sides of the vehicle. The system is low-power and processes scenes entirely on the microprocessor of an embedded smart camera. In contrast to most existing work that addresses either daytime or nighttime detection, the presented system provides the ability to track vehicle taillights and detect alert signals regardless of lighting conditions. The mobile vision system has been tested in actual traffic scenes and the results obtained demonstrate the performance and the lightweight nature of the algorithm.

show abstract

Section: A Survey Of State-of-the-art Researchmentioning

confidence: 99%

“…Most mobile headlight detection approaches are based on either local features (time-independent information obtained from every frame via morphological operations and fixed-value intensity thresholds [41], [39]) or temporal information (timedependent information used for tracking [38], [40], [37]). …”

Section: A Survey Of State-of-the-art Researchmentioning

confidence: 99%

Robust and Computationally Lightweight Autonomous Tracking of Vehicle Taillights and Signal Detection by Embedded Smart Cameras

Almagambetov

Velipasalar

Casares

2015

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

show abstract

“…To correspond to the various sizes of the light of the vehicle, it is necessary to derive response from multiple scales of LoG operator, but the calculation time is large for practical use. Therefore, we use Center Surround Extremas (CenSurE) [19], which uses an integral image for deriving multiple scales of approximated LoG operator to detect blobs in high speed [20]. The objective of this study is to set the parameter of CenSurE to a value that suppresses the falsenegatives, and remove the false-positives by post processing.…”

Section: Introductionmentioning

confidence: 99%

Vision-Based Nighttime Vehicle Detection Using CenSurE and SVM

Kosaka

Ohashi

2015

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a method for detecting vehicles from a nighttime driving scene taken by an in-vehicle monocular camera. Since it is difficult to recognize the shape of the vehicles during nighttime, vehicle detection is based on the headlights and the taillights, which are bright areas of pixels called blobs. Many research studies using automatic multilevel thresholding are being conducted, but these methods are prone to get affected by the ambient light because it uses the luminance of the whole image to derive the thresholds. Owing to such reasons, we focused on the Laplacian of Gaussian operator, which derives the response of luminance difference between the blob and its surroundings. Compared with automatic multilevel thresholding, Laplacian of Gaussian operator is more robust to the ambient light. However, the computational cost to derive the response of this operator is large. Therefore, we used a method called Center Surround Extremas to detect the blobs in high speed. Since the detected blobs include nuisance lights, we had to determine whether the blob is a light of a vehicle or not. Thus, we classified them according to the features of the blob using support vector machines. Then, we detected vehicle traffic lane and specified the region where the vehicle may exist. Finally, we classified the blobs based on the movements across the frames. We applied the proposed method to nighttime driving sequences and confirmed the effectiveness of the classification process used in this method and that it could process within frame rate.

show abstract

“…Other vehicle light detections systems have been reported, such as a grayscale image [ 11 ] and the OTSU algorithm [ 12 ] or blob detection technique [ 13 , 14 , 15 ]. In addition, methods using these studies used a Region of Interest (ROI) [ 12 , 16 ]. A probabilistic tracking method which can be used to represent the associations of two blobs from different frames, has also been reported [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image-Based Night-Time Vehicle Light Detection Using Spectral Normalization and Distance Mapper for Intelligent Headlight Control

Kim

Kwon

Kim

2016

Sensors

View full text Add to dashboard Cite

This paper proposes a vehicle light detection method using a hyperspectral camera instead of a Charge-Coupled Device (CCD) or Complementary metal-Oxide-Semiconductor (CMOS) camera for adaptive car headlamp control. To apply Intelligent Headlight Control (IHC), the vehicle headlights need to be detected. Headlights are comprised from a variety of lighting sources, such as Light Emitting Diodes (LEDs), High-intensity discharge (HID), and halogen lamps. In addition, rear lamps are made of LED and halogen lamp. This paper refers to the recent research in IHC. Some problems exist in the detection of headlights, such as erroneous detection of street lights or sign lights and the reflection plate of ego-car from CCD or CMOS images. To solve these problems, this study uses hyperspectral images because they have hundreds of bands and provide more information than a CCD or CMOS camera. Recent methods to detect headlights used the Spectral Angle Mapper (SAM), Spectral Correlation Mapper (SCM), and Euclidean Distance Mapper (EDM). The experimental results highlight the feasibility of the proposed method in three types of lights (LED, HID, and halogen).

show abstract

Vehicles detection based on extremas in nighttime driving scene

Cited by 10 publications

References 12 publications

Robust and Computationally Lightweight Autonomous Tracking of Vehicle Taillights and Signal Detection by Embedded Smart Cameras

Robust and Computationally Lightweight Autonomous Tracking of Vehicle Taillights and Signal Detection by Embedded Smart Cameras

Vision-Based Nighttime Vehicle Detection Using CenSurE and SVM

Hyperspectral Image-Based Night-Time Vehicle Light Detection Using Spectral Normalization and Distance Mapper for Intelligent Headlight Control

Contact Info

Product

Resources

About