A Novel System for Nighttime Vehicle Detection Based on Foveal Classifiers With Real-Time Performance

Bell, Andrés; Mantecón, Tomás; Díaz, César; del-Blanco, Carlos R.; Jaureguizar, Fernando; García, Narciso

doi:10.1109/tits.2021.3053863

Cited by 28 publications

(15 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the analysis of the detection results raised concerns whether an annotation method with bounding boxes (even if most commonly used) is a good annotation scheme for light artifacts due to a high annotation uncertainty because of unclear object boundaries-light artifacts are fuzzy and of weak intensity such that clear boundaries are missing. These results are partly orthogonal to Bell et al, 2021, where the authors annotated vehicles in nighttime images of traffic surveillance cameras with keypoints because the blurry edges of the vehicles due to motion blur and the saturated pixels due to the bright light cones of vehicles headlamps did not allow a reliable annotation of the vehicles by bounding boxes.…”

Section: Provident Vehicle Detectionmentioning

confidence: 85%

“…At nighttime, due to low contrast, vehicles are usually detected by locating their headlamps and rear lights singularities in the image space caused by the luminous intensity of the light sources with rule-based algorithms (e. g., López et al, 2008, Alcantarilla et al, 2011, Eum & Jung, 2013, Sevekar & Dhonde, 2016, Pham & Yoo, 2020. However, besides rule-based approaches, methods using NNs (e. g., Oldenziel et al, 2020, Mo et al, 2019, Bell et al, 2021 or different imaging sensors like infrared cameras (e. g., Tehrani et al, 2014, Niknejad et al, 2011 have been investigated as well.…”

Section: Vehicle Detectionmentioning

confidence: 99%

“…The annotation by keypoints causes the difficulty that the majority of state-of-the-art object detectors cannot be applied because they require bounding boxes (e. g., Liu et al, 2019). For this reason, Bell et al, 2021 used foveal classifiers (a set of classifiers where each classifier is trained to provide the classification result for a particular image region). The disadvantage of this approach is that the localization performance depends on the number of classifiers and their distribution over the image.…”

Section: Provident Vehicle Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Provident vehicle detection at night for advanced driver assistance systems

Ewecker¹,

Asan

Ohnemus

et al. 2022

Auton Robot

View full text Add to dashboard Cite

In recent years, computer vision algorithms have become more powerful, which enabled technologies such as autonomous driving to evolve rapidly. However, current algorithms mainly share one limitation: They rely on directly visible objects. This is a significant drawback compared to human behavior, where visual cues caused by objects (e. g., shadows) are already used intuitively to retrieve information or anticipate occurring objects. While driving at night, this performance deficit becomes even more obvious: Humans already process the light artifacts caused by the headlamps of oncoming vehicles to estimate where they appear, whereas current object detection systems require that the oncoming vehicle is directly visible before it can be detected. Based on previous work on this subject, in this paper, we present a complete system that can detect light artifacts caused by the headlights of oncoming vehicles so that it detects that a vehicle is approaching providently (denoted as provident vehicle detection). For that, an entire algorithm architecture is investigated, including the detection in the image space, the three-dimensional localization, and the tracking of light artifacts. To demonstrate the usefulness of such an algorithm, the proposed algorithm is deployed in a test vehicle to use the detected light artifacts to control the glare-free high beam system proactively (react before the oncoming vehicle is directly visible). Using this experimental setting, the provident vehicle detection system’s time benefit compared to an in-production computer vision system is quantified. Additionally, the glare-free high beam use case provides a real-time and real-world visualization interface of the detection results by considering the adaptive headlamps as projectors. With this investigation of provident vehicle detection, we want to put awareness on the unconventional sensing task of detecting objects providently (detection based on observable visual cues the objects cause before they are visible) and further close the performance gap between human behavior and computer vision algorithms to bring autonomous and automated driving a step forward.

show abstract

Section: Provident Vehicle Detectionmentioning

confidence: 85%

Section: Vehicle Detectionmentioning

confidence: 99%

Section: Provident Vehicle Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Provident vehicle detection at night for advanced driver assistance systems

Ewecker¹,

Asan

Ohnemus

et al. 2022

Auton Robot

View full text Add to dashboard Cite

show abstract

“…It provides a theoretical reference for further practical application. In the follow-up work, some researchers are concerned about how to improve the detection accuracy of [ 7 , 41 , 42 ] at night and under bad weather conditions, and further improvement of the detection accuracy will also be our next research direction.…”

Section: Discussionmentioning

confidence: 99%

A Real‐Time Object Detector for Autonomous Vehicles Based on YOLOv4

Wang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Object detection is an important part of autonomous driving technology. To ensure the safe running of vehicles at high speed, real-time and accurate detection of all the objects on the road is required. How to balance the speed and accuracy of detection is a hot research topic in recent years. This paper puts forward a one-stage object detection algorithm based on YOLOv4, which improves the detection accuracy and supports real-time operation. The backbone of the algorithm doubles the stacking times of the last residual block of CSPDarkNet53. The neck of the algorithm replaces the SPP with the RFB structure, improves the PAN structure of the feature fusion module, adds the attention mechanism CBAM and CA structure to the backbone and neck structure, and finally reduces the overall width of the network to the original 3/4, so as to reduce the model parameters and improve the inference speed. Compared with YOLOv4, the algorithm in this paper improves the average accuracy on KITTI dataset by 2.06% and BDD dataset by 2.95%. When the detection accuracy is almost unchanged, the inference speed of this algorithm is increased by 9.14%, and it can detect in real time at a speed of more than 58.47 FPS.

show abstract

“…Deep learning-based methods have been studied to address challenges in the model-based method. Object detection methods using the bounding box are used for autonomous driving, and recent studies [12][13][14] propose improved methods to obtain robust results in a variety of weather and light conditions. Methods for improving detection accuracy [15] and computing efficiency [16] have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Vision-Based Branch Road Detection for Intersection Navigation in Unstructured Environment Using Multi-Task Network

Ahn

Lee

Kim

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

Autonomous vehicles need a driving method to be less dependent on localization data to navigate intersections in unstructured environments because these data may not be accurate in such environments. Methods of distinguishing branch roads existing at intersections using vision and applying them to intersection navigation have been studied. Model-based detection methods recognize patterns of the branch roads, but are sensitive to sensor noise and difficult to apply to various complex situations. Therefore, this study proposes a method for detecting the branch roads at the intersection using deep learning. The proposed multi-task deep neural network distinguishes the branch road into a shape of rotated bounding boxes and also recognizes the drivable area to consider obstacles inside the box. Through the output of the network, an occupancy grid map consisting of one branch road at an intersection is obtained, which can be used as an input to the existing motion-planning algorithms that do not consider intersections. Experiments in real environments show that the proposed method detected the branch roads more accurately than the model-based detection method, and the vehicle drove safely at the intersection.

show abstract

A Novel System for Nighttime Vehicle Detection Based on Foveal Classifiers With Real-Time Performance

Cited by 28 publications

References 38 publications

Provident vehicle detection at night for advanced driver assistance systems

Provident vehicle detection at night for advanced driver assistance systems

A Real‐Time Object Detector for Autonomous Vehicles Based on YOLOv4

Vision-Based Branch Road Detection for Intersection Navigation in Unstructured Environment Using Multi-Task Network

Contact Info

Product

Resources

About