Accelerated Fog Removal from Real Images for Car Detection

Younis, Rawan; Bastaki, Nabil

doi:10.1109/ieeegcc.2017.8448075

Cited by 11 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to visibility, we classified foggy weather into one of four conditions, as shown in Table 1 . We determined the visibility for each individual traffic scenario in the experiment based on [ 2 , 9 , 10 ]. In clear weather, the visibility distance is greater than 1000 m, while that in light fog is 500–800 m, in medium fog is 300–500 m, and in heavy fog is 50–200 m. The total number of images is 25,000, with 80% (20,000) belonging to the training set and the remaining 5000 for testing and verification.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Camera–Radar Fusion with an Attention Framework for Autonomous Vehicle Vision in Foggy Weather Conditions

Ogunrinde

Bernadin

2023

Sensors

View full text Add to dashboard Cite

AVs are affected by reduced maneuverability and performance due to the degradation of sensor performances in fog. Such degradation can cause significant object detection errors in AVs’ safety-critical conditions. For instance, YOLOv5 performs well under favorable weather but is affected by mis-detections and false positives due to atmospheric scattering caused by fog particles. The existing deep object detection techniques often exhibit a high degree of accuracy. Their drawback is being sluggish in object detection in fog. Object detection methods with a fast detection speed have been obtained using deep learning at the expense of accuracy. The problem of the lack of balance between detection speed and accuracy in fog persists. This paper presents an improved YOLOv5-based multi-sensor fusion network that combines radar object detection with a camera image bounding box. We transformed radar detection by mapping the radar detections into a two-dimensional image coordinate and projected the resultant radar image onto the camera image. Using the attention mechanism, we emphasized and improved the important feature representation used for object detection while reducing high-level feature information loss. We trained and tested our multi-sensor fusion network on clear and multi-fog weather datasets obtained from the CARLA simulator. Our results show that the proposed method significantly enhances the detection of small and distant objects. Our small CR-YOLOnet model best strikes a balance between accuracy and speed, with an accuracy of 0.849 at 69 fps.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Machine vision in fog can fall as low as 1000 m in moderate fog and as low as 50 m in heavy fog [ 9 , 10 ]. Camera sensors are one of the significant sensors used for object detection because of their low cost and the large number of features they provide [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Camera–Radar Fusion with an Attention Framework for Autonomous Vehicle Vision in Foggy Weather Conditions

Ogunrinde

Bernadin

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In order to demonstrate these benefits, we apply our knowledge on two automotive case studies used in modern vehicles' environment perception: a model-based generated safety-critical automotive task, implementing a sobel filter for edge detection and a pedestrian detection task [21]. The former, edge detection, is very common in both ADAS (Advanced Driving Assistance Systems) and autonomous driving for numerous tasks such as lane departure [17], sign [22] and car detection [27]. Pedestrian detection is also used for ADAS, eg.…”

Section: Exploiting the Knowledge Of Gpu Allocators In Automotive Casmentioning

confidence: 99%

Gmai

Calderon

Kosmidis

Nicolás

et al. 2020

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

Critical real-time systems require strict resource provisioning in terms of memory and timing. The constant need for higher performance in these systems has led industry to recently include GPUs. However, GPU software ecosystems are by their nature closed source, forcing system engineers to consider them as black boxes, complicating resource provisioning. In this work we reverse engineer the internal operations of the GPU system software to increase the understanding of their observed behaviour and how resources are internally managed. We present our methodology which is incorporated in GMAI (GPU Memory Allocation Inspector), a tool which allows system engineers to accurately determine the exact amount of resources required by their critical systems, avoiding underprovisioning. We first apply our methodology on a wide range of GPU hardware from different vendors showing its generality in obtaining the properties of the GPU memory allocators. Next, we demonstrate the benefits of such knowledge in resource provisioning of two case studies from the automotive domain, where the actual memory consumption is up to 5.6× more than the memory requested by the application.

show abstract

“…In order to demonstrate these benefits, we apply our knowledge on two automotive case studies used in modern vehicles' environment perception: a model-based generated safety-critical automotive task, implementing a sobel filter for edge detection and a pedestrian detection task [12]. The former, edge detection, is very common in both ADAS (Advanced Driving Assistance Systems) and autonomous driving for numerous tasks such as lane departure [13], sign [14] and car detection [15]. Pedestrian detection is also used for ADAS, eg.…”

Section: B Exploiting the Knowledge Of Cuda Allocators In Automotive Case Studies' Resource Provisioningmentioning

confidence: 99%

Understanding and Exploiting the Internals of GPU Resource Allocation for Critical Systems

Calderon

Kosmidis

Nicolás

et al. 2019

2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)

View full text Add to dashboard Cite

Critical real-time systems require strict resource provisioning in terms of memory and timing. The constant need for higher performance in these systems has led industry to recently include GPUs. However, GPU software ecosystems are by their nature closed source, forcing system engineers to consider them as black boxes, complicating resource provisioning. In this work we reverse engineer the internal operations of the GPU system software to increase the understanding of their observed behaviour and how resources are internally managed. This way, we allow system engineers to accurately determine the exact amount of resources required by their critical systems, avoiding underprovisioning. We first apply our methodology on a wide range of GPU hardware showing its generality in obtaining the properties of the GPU memory allocators. Next, we demonstrate the benefits of such knowledge in resource provisioning of two case studies from the automotive domain, where the actual memory consumption is up to 5.6× more than the memory requested by the application.

show abstract

Accelerated Fog Removal from Real Images for Car Detection

Cited by 11 publications

References 6 publications

Deep Camera–Radar Fusion with an Attention Framework for Autonomous Vehicle Vision in Foggy Weather Conditions

Deep Camera–Radar Fusion with an Attention Framework for Autonomous Vehicle Vision in Foggy Weather Conditions

Gmai

Understanding and Exploiting the Internals of GPU Resource Allocation for Critical Systems

Contact Info

Product

Resources

About