Robust Grape Detector Based on SVMs and HOG Features

Škrabánek, Pavel; Doležel, Petr

doi:10.1155/2017/3478602

Cited by 13 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also consider that the time complexity of the system can be reduced once the object image contains only the heads of the passengers (omitting the shoulders will result in smaller object images and consequently reduce data processing time). We deduce the suitability of such an approach from remarkable results of HOG-based object recognition systems on similar tasks, e.g., for grape detection [31,32] (see Figure 3; the round shape of grapes is similar to the shape of heads).…”

Section: Introductionmentioning

confidence: 99%

Person Detection for an Orthogonally Placed Monocular Camera

Škrabánek

Doležel

Němec

et al. 2020

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

Counting of passengers entering and exiting means of transport is one of the basic functionalities of passenger flow monitoring systems. Exact numbers of passengers are important in areas such as public transport surveillance, passenger flow prediction, transport planning, and transport vehicle load monitoring. To allow mass utilization of passenger flow monitoring systems, their cost must be low. As the overall price is mainly given by prices of the used sensor and processing unit, we propose the utilization of a visible spectrum camera and data processing algorithms of low time complexity to ensure a low price of the final product. To guarantee the anonymity of passengers, we suggest orthogonal scanning of a scene. As the precision of the counting is relevantly influenced by the precision of passenger recognition, we focus on the development of an appropriate recognition method. We present two opposite approaches which can be used for the passenger recognition in means of transport with and without entrance steps, or with split level flooring. The first approach is the utilization of an appropriate convolutional neural network (ConvNet), which is currently the prevailing approach in computer vision. The second approach is the utilization of histograms of oriented gradients (HOG) features in combination with a support vector machine classifier. This approach is a representative of classical methods. We study both approaches in terms of practical applications, where real-time processing of data is one of the basic assumptions. Specifically, we examine classification performance and time complexity of the approaches for various topologies and settings, respectively. For this purpose, we form and make publicly available a large-scale, class-balanced dataset of labelled RGB images. We demonstrate that, compared to ConvNets, the HOG-based passenger recognition is more suitable for practical applications. For an appropriate setting, it defeats the ConvNets in terms of time complexity while keeping excellent classification performance. To allow verification of theoretical findings, we construct an engineering prototype of the system.

show abstract

Section: Introductionmentioning

confidence: 99%

Person Detection for an Orthogonally Placed Monocular Camera

Škrabánek

Doležel

Němec

et al. 2020

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

show abstract

“…2. The structure of the detector is based on authors' previous experience published in [Skrabanek 2015[Skrabanek , 2016[Skrabanek and 2017. Globally, the structure fits on any pattern recognition system, but each part is redesigned in order to fit the person detection.…”

Section: Problem Formulation and Metodologymentioning

confidence: 99%

Development of Image Procesing System for Person Detection

Štursa¹,

Honc²,

Doležel³

2020

MM SJ

View full text Add to dashboard Cite

With the rise of modern technology in computer science and engineering, as well as with the growing population in big cities around the world, many new approaches for person detection have become a very interesting and demanding topic. Person detection is a necessary building block for people monitoring systems and, therefore, various detection methods must be inspected comprehensively in order to select the one with the most suitable performance and accuracy. In this paper, a set of different image processing techniques applied to images captured from a high angle were used for people detection. To be more specific, selected feature extraction techniques, like edge detectors, local binary patterns, pixel intensities or histograms of oriented gradients, were used in combination with several classification algorithms. The combinations of each feature extractor and its best classifier were selected for performance comparison. As a result of the comparison, the most suitable image processing method for person detection in high angle image is presented at the end of the paper.

show abstract

“…2 for a basic illustration of the functionality. The structure of the detector is based on our previous work [25], [24] and [23]. Nevertheless, each part of the detector is redesigned in order to fit to the new purpose.…”

Section: Problem Formulationmentioning

confidence: 99%

“…Although a totally different problem, the grape shape is similar to a head. And in the research summarized in [23] and [24], histograms of oriented gradients have proven to be an optimal tool for feature extraction.…”

Section: Introductionmentioning

confidence: 99%

On Possibilities of Human Head Detection for Person Flow Monitoring System

Doležel

Štursa

Škrabánek

2019

Advances in Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Along with the development of human society, economy, industry and engineering, as well as with growing population in the world's biggest cities, various approaches to person detection have become the subject of great interest. One approach to developing a person detection system is proposed in this paper. A high-angle video sequence is considered as the input to the system. Then, three classification algorithms are considered: support vector machines, pattern recognition neural networks and convolutional neural networks. The results showed very little difference between the classifiers, with the overall accuracy more than 95 % over a testing set.

show abstract

Robust Grape Detector Based on SVMs and HOG Features

Cited by 13 publications

References 15 publications

Person Detection for an Orthogonally Placed Monocular Camera

Person Detection for an Orthogonally Placed Monocular Camera

Development of Image Procesing System for Person Detection

On Possibilities of Human Head Detection for Person Flow Monitoring System

Contact Info

Product

Resources

About