A new architecture based on convolutional neural networks (CNN) for assisting the driver in fog environment

Allach, Samir; Mohamed, Ben Ahmed; Abdelhakim, Boudhir Anouar

doi:10.1145/3286606.3286862

Cited by 4 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guo et al ( 2022 ) first proposed a data set for vehicle detection on foggy highway, and then proposed a foggy vehicle detection model based on improved generative adversarial network and YOLOv4, which effectively improves vehicle detection performance and has strong universality for low-visibility applications based on computer vision. Samir et al ( 2018 ) proposed a methodology for target detection during foggy days. The model employed convolutional neural networks for image removal and Fast R-CNN for target detection.…”

Section: Related Workmentioning

confidence: 99%

Real-time vehicle target detection in inclement weather conditions based on YOLOv4

Wang

Zhao

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

As a crucial component of the autonomous driving task, the vehicle target detection algorithm directly impacts driving safety, particularly in inclement weather situations, where the detection precision and speed are significantly decreased. This paper investigated the You Only Look Once (YOLO) algorithm and proposed an enhanced YOLOv4 for real-time target detection in inclement weather conditions. The algorithm uses the Anchor-free approach to tackle the problem of YOLO preset anchor frame and poor fit. It better adapts to the detected target size, making it suitable for multi-scale target identification. The improved FPN network transmits feature maps to unanchored frames to expand the model's sensory field and maximize the utilization of model feature data. Decoupled head detecting head to increase the precision of target category and location prediction. The experimental dataset BDD-IW was created by extracting specific labeled photos from the BDD100K dataset and fogging some of them to test the proposed method's practical implications in terms of detection precision and speed in Inclement weather conditions. The proposed method is compared to advanced target detection algorithms in this dataset. Experimental results indicated that the proposed method achieved a mean average precision of 60.3%, which is 5.8 percentage points higher than the original YOLOv4; the inference speed of the algorithm is enhanced by 4.5 fps compared to the original, reaching a real-time detection speed of 69.44 fps. The robustness test results indicated that the proposed model has considerably improved the capacity to recognize targets in inclement weather conditions and has achieved high precision in real-time detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-time vehicle target detection in inclement weather conditions based on YOLOv4

Wang

Zhao

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…B Michal Jasinski michal.jasinski@pwr.edu.pl Extended author information available on the last page of the article dimensional verification of crankshafts [15], detection of objects [29]), geo engineering (maps classification [2], detection of Earth's surface features changes [34]), industrial applications (package inspection [17], sorting [6], quality inspection [36]).…”

Section: Introductionmentioning

confidence: 99%

A Power-Efficient Multichannel Low-Pass Filter Based on the Cascaded Multiple Accumulate Finite Impulse Response (CMFIR) Structure for Digital Image Processing

Jain¹,

Chakrabarti²,

Mitolo

et al. 2022

Circuits Syst Signal Process

View full text Add to dashboard Cite

The author offers a power-efficient multichannel low-pass filter for digital image processing based on the cascade multiple accumulate finite impulse response (CMFIR) structure in this study. The CMFIR filter was created using the outputs of a linear time-invariant system (LTI), which was built using a cascaded integrator comb (CIC) and a MAC low-pass filter. The sample rate convertor based on CIC filters effectively conducts decimation or interpolation. The sample rate convertor with the CIC filter can only accommodate narrowband transmissions and so cannot be utilized for wideband signals. The MAC architecture-based sample rate convertor is a good solution for high-bandwidth signals, but it uses more resources like registers and flip-flops, which increases power consumption. Here, the CMFIR low-pass filter acts as an interpolator, introducing a sample to boost the image's resolution. CMFIR is a useful tool for addressing the issue of aliasing during sampling. In addition, the genetic algorithm was used to increase the filter's resource utilization and power consumption efficiency.

show abstract

“…However, the target smoke can be removed by the algorithms sometimes due to the clutter and unclear contents in the foggy surveillance, which affects the detection performance. Therefore, some deep learning based methods are proposed to directly perform detection tasks in harsh environments, such as [16,18,28].…”

Section: Introductionmentioning

confidence: 99%

Dark-Channel Mixed Attention Based Neural Networks for Smoke Detection in Fog Environment

Yang

Gong

et al. 2021

Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of The

View full text Add to dashboard Cite

Although deep learning has been widely applied to smoke detection tasks, most of these methods only consider the problem in normal weather, which leads to a drastic performance decreasing when detecting smoke in fog. Existing methods propose to add the synthetic fog to the images collected in normal environments, and to train the models on the augmented datasets. However, these methods only alleviate the problem. Due to that the generalization ability of a machine learning method can only be guaranteed if training and test datasets are with the same data distribution, the distribution gap between synthetic and real-world images limits the upper bound of the detection performance. In this paper, we develop a general smoke detection dataset with diverse real-world collected samples. Furthermore, we develop a novel smoke detection method based on dark-channel assisted mixed attention. Experiments show the importance of the built dataset and the effectiveness of our detection method.

show abstract

A new architecture based on convolutional neural networks (CNN) for assisting the driver in fog environment

Cited by 4 publications

References 13 publications

Real-time vehicle target detection in inclement weather conditions based on YOLOv4

Real-time vehicle target detection in inclement weather conditions based on YOLOv4

A Power-Efficient Multichannel Low-Pass Filter Based on the Cascaded Multiple Accumulate Finite Impulse Response (CMFIR) Structure for Digital Image Processing

Dark-Channel Mixed Attention Based Neural Networks for Smoke Detection in Fog Environment

Contact Info

Product

Resources

About