Deep Learning based Pedestrian Detection at all Light Conditions

Chebrolu, Koti Naga Renu; N., Col.) Kumar P.

doi:10.1109/iccsp.2019.8698101

Cited by 31 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An illumination aware Faster R-CNN deep learning based convolutional neural network architecture is employed by [14] for pedestrian detection in both infrared and color images. A brightness aware deep learning based mechanism is proposed by [15] and it is used to detect pedestrians under day or night conditions respectively. An automatic region proposal network is introduced by [16] to generate bounding boxes with confidence scores for farinfrared (FIR) pedestrian detection.…”

Section: A Pedestrian Detection In Infrared Imagesmentioning

confidence: 99%

Pedestrian Street-Cross Action Recognition in Monocular Far Infrared Sequences

et al. 2021

View full text Add to dashboard Cite

The early recognition and understanding of the actions performed by pedestrians in traffic scenes leads to an anticipation of pedestrian intentions in advance and helps in the process of collision warning and avoidance in the context of autonomous vehicles. An environment with low visibility conditions such as night-time, fog, heavy rain or smoke increases the number of difficult situations in traffic. A complete and original model for assessing if a pedestrian is engaged in a street cross action using only infrared monocular scene perception is proposed in this paper. The assessment of a street cross action is done by the time series analysis of features like: pedestrian motion, position of pedestrians with respect to the drivable area and their distance with respect to the ego-vehicle. The extraction of these features emerges from the combination of a deep learning based pedestrian detector with an original tracking algorithm, a semantic segmentation of the road surface and a time series long-short term memory network based action recognition. In order to validate the proposed method we introduce a new dataset named CROSSIR. It is formed of pedestrian annotations, action annotations and semantic labels for the road. The CROSSIR dataset is suitable for several common computer vision algorithms: (1) pedestrian detection and tracking algorithms because each pedestrian has a unique identifier over the frames in which it appears; (2) pedestrian action recognition; (3) semantic segmentation of the road pixels in the infrared image.

show abstract

Section: A Pedestrian Detection In Infrared Imagesmentioning

confidence: 99%

Pedestrian Street-Cross Action Recognition in Monocular Far Infrared Sequences

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The second approach was proposed by Chebrolu and Kumar [33]. They developed a brightness awareness model.…”

Section: Pedestrian Detection At Different Lighting Conditionsmentioning

confidence: 99%

Pedestrian Detection Using Multispectral Images and a Deep Neural Network

Nataprawira

Goncharenko

et al. 2021

Sensors

View full text Add to dashboard Cite

Pedestrian fatalities and injuries most likely occur in vehicle-pedestrian crashes. Meanwhile, engineers have tried to reduce the problems by developing a pedestrian detection function in Advanced Driver-Assistance Systems (ADAS) and autonomous vehicles. However, the system is still not perfect. A remaining problem in pedestrian detection is the performance reduction at nighttime, although pedestrian detection should work well regardless of lighting conditions. This study presents an evaluation of pedestrian detection performance in different lighting conditions, then proposes to adopt multispectral image and deep neural network to improve the detection accuracy. In the evaluation, different image sources including RGB, thermal, and multispectral format are compared for the performance of the pedestrian detection. In addition, the optimizations of the architecture of the deep neural network are performed to achieve high accuracy and short processing time in the pedestrian detection task. The result implies that using multispectral images is the best solution for pedestrian detection at different lighting conditions. The proposed deep neural network accomplishes a 6.9% improvement in pedestrian detection accuracy compared to the baseline method. Moreover, the optimization for processing time indicates that it is possible to reduce 22.76% processing time by only sacrificing 2% detection accuracy.

show abstract

“…Ziadia et al [10] also observed that winter conditions reduce pedestrian and distant vehicles' detection rate. Chebrolu et al [11] have mentioned that most models fail to predict pedestrians in a dark environment. Winter increases dark environments' durations.…”

Section: Introductionmentioning

confidence: 99%

“…Network-tonetwork transfer can be done via automatic image annotation [37][38][39][40] or weight transfer such as pre-training and sharing a backbone. Srinivas et al [41] adapted this concept for pedestrian detection, allowing the research community to access the teacher-student networks for autonomous driving. In short, by using a high discriminative network as a teacher to a high capacity one, it is possible to obtain a high-capacity network.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attention transfer from human to neural networks for road object detection in winter

Boisclair

Kélouwani

Ayevide

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

As an essential feature of autonomous road vehicles, obstacle detection must be executed on a real‐time onboard platform with high accuracy. Cameras are still the most commonly used sensors in autonomous driving. Most detections using cameras are based on convolutional neural networks. In this regard, a recent teacher–student approach, called transfer learning, has been used to improve the neural network training process. This approach has only been used with a neural network acting as a teacher to the best of our knowledge. This paper proposes a novel way of improving training data based on attention transfer by getting the attention map from a human. The proposed method allows the dataset size reduction by 50%, which leads to up to a 60% decline in the training time. The experimental results indicate that the proposed method can enhance the F1‐score of the network by up to 10% in winter conditions.

show abstract

Deep Learning based Pedestrian Detection at all Light Conditions

Cited by 31 publications

References 9 publications

Pedestrian Street-Cross Action Recognition in Monocular Far Infrared Sequences

Pedestrian Street-Cross Action Recognition in Monocular Far Infrared Sequences

Pedestrian Detection Using Multispectral Images and a Deep Neural Network

Attention transfer from human to neural networks for road object detection in winter

Contact Info

Product

Resources

About