Three-level cascade of random forests for rapid human detection

Ko, Byoung Chul; Kim, Deok-Yeon; Jung, Jihoon; Nam, Jae-Yeal

doi:10.1117/1.oe.52.2.027204

Cited by 20 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, different kinds of variants have been developed to solve particular problems. The center symmetric local binary pattern (CSLBP) is designed by comparing the center-symmetric pairs of pixels with a central pixel rather than comparing each pixel with the center [ 9 ]. The CSLBP approach maintains certain characteristics of rotation invariability and gray-level invariability, while reducing computational cost [ 7 , 24 ].…”

Section: Related Workmentioning

confidence: 99%

“…Human candidate pixels are supposed to be with higher intensity in the IR images because the temperature of the human body is usually higher than that of the background [ 6 ]. Although an increasing number of theories and methods have been put forward as solutions for visible light classification and detection problems [ 7 , 8 , 9 , 10 ], those for IR imagery detection have never been proposed in a systematical manner. In general, the IR spectrum can be classified into four sub-bands, such as near-IR, short-wave IR, medium-wave IR, far-infrared [ 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Channel Expansion and Background Suppression as the Enhancement for Infrared Pedestrian Detection

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Pedestrian detection is an important task in many intelligent systems, particularly driver assistance systems. Recent studies on pedestrian detection in infrared (IR) imagery have employed data-driven approaches. However, two problems in deep learning-based detection are the implicit performance and time-consuming training. In this paper, a novel channel expansion technique based on feature fusion is proposed to enhance the IR imagery and accelerate the training process. Besides, a novel background suppression method is proposed to stimulate the attention principle of human vision and shrink the region of detection. A precise fusion algorithm is designed to combine the information from different visual saliency maps in order to reduce the effect of truncation and miss detection. Four different experiments are performed from various perspectives in order to gauge the efficiency of our approach. The experimental results show that the Mean Average Precisions (mAPs) of four different datasets have been increased by 5.22% on average. The results prove that background suppression and suitable feature expansion will accelerate the training process and enhance the performance of IR image-based deep learning models.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Feature Channel Expansion and Background Suppression as the Enhancement for Infrared Pedestrian Detection

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…After selecting the image-scaling levels with their adaptive ROI, we employ a CaRF classifier by modifying the works in [ 2 , 9 ] to separate candidate windows into both human and non-human classes. CRF is a combination of a series of random forest classifiers as a filter chain, as shown in Figure 3 .…”

Section: Cascade Random Forest For Human Classificationmentioning

confidence: 99%

“…Cascade AdaBoost [ 8 ] is a representative cascade strategy for human detection, and can reject most negative sliding windows during the early stages of the cascade steps. Cascade of random forests (CaRF) [ 9 ] is a three-level cascade of random forests that combines a series of random forest classifiers into a filter chain.…”

Section: Introductionmentioning

confidence: 99%

Fast Human Detection for Intelligent Monitoring Using Surveillance Visible Sensors

Jeong

Nam

2014

Sensors

View full text Add to dashboard Cite

Human detection using visible surveillance sensors is an important and challenging work for intruder detection and safety management. The biggest barrier of real-time human detection is the computational time required for dense image scaling and scanning windows extracted from an entire image. This paper proposes fast human detection by selecting optimal levels of image scale using each level's adaptive region-of-interest (ROI). To estimate the image-scaling level, we generate a Hough windows map (HWM) and select a few optimal image scales based on the strength of the HWM and the divide-and-conquer algorithm. Furthermore, adaptive ROIs are arranged per image scale to provide a different search area. We employ a cascade random forests classifier to separate candidate windows into human and nonhuman classes. The proposed algorithm has been successfully applied to real-world surveillance video sequences, and its detection accuracy and computational speed show a better performance than those of other related methods.

show abstract

“…e hybrid features consist of the peak-to-average power ratio, short-term interval zero crossing, and fractal characteristics in the frequency domain, which not only reflect leakage states of pipelines but also represent more detailed information for multiple microstates of pipelines. Although these features cannot directly obtain the hiding pipeline state information, machine learning methods, such as support vector machine (SVM), C5.0, and randomforest algorithm, can be used to recognize the microstates of pipelines [16,17]. e experimental results prove this method based on hybrid features which can effectively improve the pipeline leakage event recognition accuracy with the classifier of random forest, whose average accuracy is above 91% on two kinds of pipeline leakage and 83% on four microstates.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Feature Extraction of Pipeline Microstates Based on Φ-OTDR Sensing System

Meng

et al. 2019

Journal of Control Science and Engineering

View full text Add to dashboard Cite

This paper proposes a general integration method which can effectively describe the characteristics of pipeline leakage and help distinguish multiple pipeline microstates. Since the rapid development of Φ-OTDR in recent years, this technology has been applied to more and more fields, such as fiber optic safety monitoring, seismic monitoring, and structural health monitoring. Among them, Φ-OTDR has the characteristic of continuous full-scale monitoring in pipeline monitoring, but there are few researches on pipeline state characteristics at present. In this paper, based on the analysis of the pipeline state with Φ-OTDR technology, a method of extracting multiple microstates of pipelines is proposed. This method combined with the peak-to-average power ratio, short-term interval zero crossing, and fractal characteristics in the frequency domain can effectively characterize the microstate of pipes and provide support for identification of more microstates of pipelines. These features reflect the common characteristics of leaks in gas pipelines and liquid pipelines. Meanwhile, their combination features can represent the small differences in pipeline states. The experimental results show that the method can effectively characterize the microstate information of the pipeline, and the recognition rate of the hybrid feature under two kinds of pipeline leakage and multipressure conditions reaches 91% and 83%.

show abstract

Three-level cascade of random forests for rapid human detection

Cited by 20 publications

References 22 publications

Feature Channel Expansion and Background Suppression as the Enhancement for Infrared Pedestrian Detection

Feature Channel Expansion and Background Suppression as the Enhancement for Infrared Pedestrian Detection

Fast Human Detection for Intelligent Monitoring Using Surveillance Visible Sensors

Hybrid Feature Extraction of Pipeline Microstates Based on Φ-OTDR Sensing System

Contact Info

Product

Resources

About