Infrared Pedestrian Detection Based on GAN Data Augmentation

2020 ◽  
Author(s):  
Jinda Hu ◽  
Yanshun Zhao ◽  
Xindong Zhang
Keyword(s):  
Data Augmentation ◽  
Pedestrian Detection

AutoPedestrian: An Automatic Data Augmentation and Loss Function Search Scheme for Pedestrian Detection

2021 ◽  
Vol 30 ◽  
pp. 8483-8496
Author(s):  
Yi Tang ◽  
Baopu Li ◽  
Min Liu ◽  
Boyu Chen ◽  
Yaonan Wang ◽  
...  
Keyword(s):  
Loss Function ◽  
Data Augmentation ◽  
Pedestrian Detection ◽  
Automatic Data

scholarly journals Toward Robust Pedestrian Detection With Data Augmentation

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 136674-136683
Author(s):  
Sebastian Cygert ◽  
Andrzej Czyzewski
Keyword(s):  
Data Augmentation ◽  
Pedestrian Detection

Pose-Guided Person Image Synthesis for Data Augmentation in Pedestrian Detection

2021 ◽  
Author(s):  
Rong Zhi ◽  
Zijie Guo ◽  
Wuqiang Zhang ◽  
Baofeng Wang ◽  
Vitali Kaiser ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Pedestrian Detection ◽  
Image Synthesis

A novel data augmentation scheme for pedestrian detection with attribute preserving GAN

2020 ◽  
Vol 401 ◽  
pp. 123-132
Author(s):  
Songyan Liu ◽  
Haiyun Guo ◽  
Jian-Guo Hu ◽  
Xu Zhao ◽  
Chaoyang Zhao ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Pedestrian Detection

scholarly journals PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

2020 ◽  
Vol 34 (07) ◽  
pp. 10639-10646
Author(s):  
Cheng Chi ◽  
Shifeng Zhang ◽  
Junliang Xing ◽  
Zhen Lei ◽  
Stan Z. Li ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Pedestrian Detection ◽  
Simulated Data ◽  
Representation Learning ◽  
Feature Representation ◽  
Occlusion Handling ◽  
Source Codes ◽  
Efficient Detection ◽  
Crowded Scenes

Pedestrian detection in crowded scenes is a challenging problem, because occlusion happens frequently among different pedestrians. In this paper, we propose an effective and efficient detection network to hunt pedestrians in crowd scenes. The proposed method, namely PedHunter, introduces strong occlusion handling ability to existing region-based detection networks without bringing extra computations in the inference stage. Specifically, we design a mask-guided module to leverage the head information to enhance the feature representation learning of the backbone network. Moreover, we develop a strict classification criterion by improving the quality of positive samples during training to eliminate common false positives of pedestrian detection in crowded scenes. Besides, we present an occlusion-simulated data augmentation to enrich the pattern and quantity of occlusion samples to improve the occlusion robustness. As a consequent, we achieve state-of-the-art results on three pedestrian detection datasets including CityPersons, Caltech-USA and CrowdHuman. To facilitate further studies on the occluded pedestrian detection in surveillance scenes, we release a new pedestrian dataset, called SUR-PED, with a total of over 162k high-quality manually labeled instances in 10k images. The proposed dataset, source codes and trained models are available at https://github.com/ChiCheng123/PedHunter.

scholarly journals Augmentation of Severe Weather Impact to Far-Infrared Sensor Images to Improve Pedestrian Detection System

Electronics ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 934
Author(s):  
Paulius Tumas ◽  
Artūras Serackis ◽  
Adam Nowosielski
Keyword(s):  
Data Augmentation ◽  
Detection System ◽  
Pedestrian Detection ◽  
Atmospheric Precipitation ◽  
Experimental Tests ◽  
Far Infrared ◽  
Weather Conditions ◽  
Severe Weather ◽  
Infrared Images ◽  
Driver Assistance Systems

Pedestrian detection is an essential task for computer vision and the automotive industry. Complex systems like advanced driver-assistance systems are based on far-infrared data sensors, used to detect pedestrians at nighttime, fog, rain, and direct sun situations. The robust pedestrian detector should work in severe weather conditions. However, only a few datasets include some examples of far-infrared images with distortions caused by atmospheric precipitation and dirt covering sensor optics. This paper proposes the deep learning-based data augmentation technique to enrich far-infrared images collected in good weather conditions by distortions, similar to those caused by bad weather. The six most accurate and fast detectors (TinyV3, TinyL3, You Only Look Once (YOLO)v3, YOLOv4, ResNet50, and ResNext50), performing faster than 15 FPS, were trained on 207,001 annotations and tested on 156,345 annotations, not used for training. The proposed data augmentation technique showed up to a 9.38 mean Average Precision (mAP) increase of pedestrian detection with a maximum of 87.02 mAP (YOLOv4). Proposed in this paper detectors’ Head modifications based on a confidence heat-map gave an additional boost of precision for all six detectors. The most accurate current detector, based on YOLOv4, reached up to 87.20 mAP during our experimental tests.

Mind wandering as data augmentation: How mental travel supports abstraction

2020 ◽  
Vol 43 ◽  
Author(s):  
Myrthe Faber
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Mental Content ◽  
Mind Wandering ◽  
Theoretical Framework ◽  
Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

2018 ◽  
Author(s):  
Alex Hernández-García ◽  
Johannes Mehrer ◽  
Nikolaus Kriegeskorte ◽  
Peter König ◽  
Tim C. Kietzmann
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation

Comparison of Nonlinear Spatial Correlation Models by the Influence of the Data Augmentation to the Classification Risk

2002 ◽  
Vol 7 (1) ◽  
pp. 31-42
Author(s):  
J. Šaltytė ◽  
K. Dučinskas
Keyword(s):  
Spatial Correlation ◽  
Random Fields ◽  
Data Augmentation ◽  
Gaussian Random Fields ◽  
Classification Rule ◽  
Numerical Comparison ◽  
First Order ◽  
Bayesian Risk ◽  
Correlation Models

The Bayesian classification rule used for the classification of the observations of the (second-order) stationary Gaussian random fields with different means and common factorised covariance matrices is investigated. The influence of the observed data augmentation to the Bayesian risk is examined for three different nonlinear widely applicable spatial correlation models. The explicit expression of the Bayesian risk for the classification of augmented data is derived. Numerical comparison of these models by the variability of Bayesian risk in case of the first-order neighbourhood scheme is performed.

Sign in / Sign up

Export Citation Format

Share Document