Joint Pedestrian and Body Part Detection via Semantic Relationship Learning

Gu, Jun; Lan, Chuanxin; Chen, Wenbai; Han, Hu

doi:10.3390/app9040752

Cited by 11 publications

(4 citation statements)

References 35 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ose networks were able to learn but were too slow in practice to be useful in real-time applications; the technique in [12] showed that stochastic gradient descent by backpropagation was effective in training CNNs. CNNs became in use but fell out of fashion due to the support vector machine as in [21] and other simpler methods like linear classifiers as in [22]. New techniques that have been developed recently [23,24] show higher image classification accuracy in ImageNet large scale visual recognition [25].…”

Section: Related Workmentioning

confidence: 99%

Object Detection through Modified YOLO Neural Network

Ahmad

Yahya

et al. 2020

Scientific Programming

135

View full text Add to dashboard Cite

In the field of object detection, recently, tremendous success is achieved, but still it is a very challenging task to detect and identify objects accurately with fast speed. Human beings can detect and recognize multiple objects in images or videos with ease regardless of the object’s appearance, but for computers it is challenging to identify and distinguish between things. In this paper, a modified YOLOv1 based neural network is proposed for object detection. The new neural network model has been improved in the following ways. Firstly, modification is made to the loss function of the YOLOv1 network. The improved model replaces the margin style with proportion style. Compared to the old loss function, the new is more flexible and more reasonable in optimizing the network error. Secondly, a spatial pyramid pooling layer is added; thirdly, an inception model with a convolution kernel of 1 ∗ 1 is added, which reduced the number of weight parameters of the layers. Extensive experiments on Pascal VOC datasets 2007/2012 showed that the proposed method achieved better performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Object Detection through Modified YOLO Neural Network

Ahmad

Yahya

et al. 2020

Scientific Programming

135

View full text Add to dashboard Cite

show abstract

“…Additionally, there are a variety of applications, including video surveillance, intelligent transportation systems, and self-driving assistance systems. Though there are many significant improvements for detecting pedestrians, the crucial yet challenging problems include the large variety of poses, appearances, sizes, and types of occlusions [4]- [6]. Among these problems, partial occlusion frequently occurs due to the diversity of the partially occluded patterns of the pedestrians, and it needs further investigation between the pedestrians and the crowded instances.…”

Section: Introductionmentioning

confidence: 99%

Pedestrian classification on transfer learning based deep convolutional neural network for partial occlusion handling

Thu

Suvonvorn

Kittiphattanabawon

2023

IJECE

View full text Add to dashboard Cite

The investigation of a deep neural network for pedestrian classification using transfer learning methods is proposed in this study. The development of deep convolutional neural networks has significantly improved the autonomous driver assistance system for pedestrian classification. However, the presence of partially occluded parts and the appearance variation under complex scenes are still robust to challenge in the pedestrian detection system. To address this problem, we proposed six transfer learning models: end-to-end convolutional neural network (CNN) model, scratch-trained residual network (ResNet50) model, and four transfer learning models: visual geometry group 16 (VGG16), GoogLeNet (InceptionV3), ResNet50, and MobileNet. The performance of the pedestrian classification was evaluated using four publicly datasets: Institut National de Recherche en Sciences et Technologies du Numérique (INRIA), Prince of Songkla University (PSU), CVC05, and Walailak University (WU) datasets. The experimental results show that six transfer learning models achieve classification accuracy of 65.2% (end-to-end CNN), 92.92% (scratch-trained ResNet50), 97.15% (pre-trained VGG16), 94.39% (pre-trained InceptionV3), 90.43% (pre-trained ResNet50), and 98.69% (pre-trained MobileNet) using data from Southern Thailand (PSU dataset). Further analysis reveals that the deeper the ConvNet architecture, the more specific information of features is provided. In addition, the deep ConvNet architecture can distinguish pedestrian occluded patterns while being trained with partially occluded parts of data samples.

show abstract

“…Pedestrian detection has attracted considerable attention from researchers in computer vision. Although many studies in pedestrian detection areas have been reported during the past decade [1][2][3][4][5][6][7][8], most of them are confined to detecting pedestrians during daytime using visible (VI) cameras. However, the performance of VI cameras depends on good illumination conditions and can be affected when illumination is poor.…”

Section: Introductionmentioning

confidence: 99%

Pedestrian Detection at Night in Infrared Images Using an Attention-Guided Encoder-Decoder Convolutional Neural Network

Chen

Shin

2020

Applied Sciences

View full text Add to dashboard Cite

Pedestrian-related accidents are much more likely to occur during nighttime when visible (VI) cameras are much less effective. Unlike VI cameras, infrared (IR) cameras can work in total darkness. However, IR images have several drawbacks, such as low-resolution, noise, and thermal energy characteristics that can differ depending on the weather. To overcome these drawbacks, we propose an IR camera system to identify pedestrians at night that uses a novel attention-guided encoder-decoder convolutional neural network (AED-CNN). In AED-CNN, encoder-decoder modules are introduced to generate multi-scale features, in which new skip connection blocks are incorporated into the decoder to combine the feature maps from the encoder and decoder module. This new architecture increases context information which is helpful for extracting discriminative features from low-resolution and noisy IR images. Furthermore, we propose an attention module to re-weight the multi-scale features generated by the encoder-decoder module. The attention mechanism effectively highlights pedestrians while eliminating background interference, which helps to detect pedestrians under various weather conditions. Empirical experiments on two challenging datasets fully demonstrate that our method shows superior performance. Our approach significantly improves the precision of the state-of-the-art method by 5.1% and 23.78% on the Keimyung University (KMU) and Computer Vision Center (CVC)-09 pedestrian dataset, respectively.

show abstract

Joint Pedestrian and Body Part Detection via Semantic Relationship Learning

Cited by 11 publications

References 35 publications

Object Detection through Modified YOLO Neural Network

Object Detection through Modified YOLO Neural Network

Pedestrian classification on transfer learning based deep convolutional neural network for partial occlusion handling

Pedestrian Detection at Night in Infrared Images Using an Attention-Guided Encoder-Decoder Convolutional Neural Network

Contact Info

Product

Resources

About