Fast object detection based on binary deep convolution neural networks

Sun, Siyang; Yin, Yingjie; Wang, Xingang; Xu, De; Wu, Wenqi; Gu, Qingyi

doi:10.1049/trit.2018.1026

Cited by 35 publications

(23 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is widely used in several completely different fields; detection of regions of interests, image editing, texture analysis, visual aesthetic and quality assessment (Datta et al, 2006; Marchesotti et al, 2011; Romero et al, 2012; Fernandez-Lozano et al, 2015; Mata et al, 2018) and more recently in Carballal et al (2019b) or for microbiome analysis (Liu et al, 2017; Roguet et al, 2018), authentication of tequilas (Pérez-Caballero et al, 2017; Andrade et al, 2017), pathogenic point mutations (Rogers et al, 2018) or forensic identification (Gómez et al, 2018). Finally, with regard to the extraction of characteristics from images, some recently published works have been revised (Xu, Wang & Wang, 2018; Ali et al, 2016b; Wang et al, 2018; Sun et al, 2018; Zafar et al, 2018b).…”

Section: Methodsmentioning

confidence: 99%

Visual complexity modelling based on image features fusion of multiple kernels

Fernández-Lozano

Carballal

Machado

et al. 2019

PeerJ

View full text Add to dashboard Cite

Humans’ perception of visual complexity is often regarded as one of the key principles of aesthetic order, and is intimately related to the physiological, neurological and, possibly, psychological characteristics of the human mind. For these reasons, creating accurate computational models of visual complexity is a demanding task. Building upon on previous work in the field (Forsythe et al., 2011; Machado et al., 2015) we explore the use of Machine Learning techniques to create computational models of visual complexity. For that purpose, we use a dataset composed of 800 visual stimuli divided into five categories, describing each stimulus by 329 features based on edge detection, compression error and Zipf’s law. In an initial stage, a comparative analysis of representative state-of-the-art Machine Learning approaches is performed. Subsequently, we conduct an exhaustive outlier analysis. We analyze the impact of removing the extreme outliers, concluding that Feature Selection Multiple Kernel Learning obtains the best results, yielding an average correlation to humans’ perception of complexity of 0.71 with only twenty-two features. These results outperform the current state-of-the-art, showing the potential of this technique for regression.

show abstract

Section: Methodsmentioning

confidence: 99%

Visual complexity modelling based on image features fusion of multiple kernels

Fernández-Lozano

Carballal

Machado

et al. 2019

PeerJ

View full text Add to dashboard Cite

show abstract

“…The detection accuracy is poor, and far less than that of YOLO v3. Also, it is proposed recently that convolution kernels of different sizes could be used to predict classes and bounding boxes of multi-scale objects directly in the last feature map of a deep CNN for rapid object detection with acceptable precision loss is achieved [35].…”

Section: The Fusion Of Multi-scaled Featuresmentioning

confidence: 99%

An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks

Cao

Chen

Gao

2020

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

IntroductionThe main purpose of object detection is to identify and locate one or more effective targets from still image or video data. It comprehensively includes a variety of important techniques, such as image processing, pattern recognition, artificial intelligence and machine learning. It has broad application prospects in such areas such as road traffic accident prevention [1], warnings of dangerous goods in factories, military restricted area monitoring and advanced human-computer interaction [2,3]. Since the application scenarios of multi-target detection in the real world are usually complex and variable, balancing the relationship between accuracy and computing costs is a difficult task.The object detection process is traditionally established by manually extracting feature models, where the common features are represented by HOG (histogram of oriented AbstractObject detection methods aim to identify all target objects in the target image and determine the categories and position information in order to achieve machine vision understanding. Numerous approaches have been proposed to solve this problem, mainly inspired by methods of computer vision and deep learning. However, existing approaches always perform poorly for the detection of small, dense objects, and even fail to detect objects with random geometric transformations. In this study, we compare and analyse mainstream object detection algorithms and propose a multi-scaled deformable convolutional object detection network to deal with the challenges faced by current methods. Our analysis demonstrates a strong performance on par, or even better, than state of the art methods. We use deep convolutional networks to obtain multi-scaled features, and add deformable convolutional structures to overcome geometric transformations. We then fuse the multi-scaled features by up sampling, in order to implement the final object recognition and region regress. Experiments prove that our suggested framework improves the accuracy of detecting small target objects with geometric deformation, showing significant improvements in the trade-off between accuracy and speed.

show abstract

“…Machine learning is widely used in several completely different fields; detection of regions of interests, image editing, texture analysis, visual aesthetic and quality assessment (Datta et al, 2006;Marchesotti et al, 2011;Romero et al, 2012;Fernandez-Lozano et al, 2015;Mata et al, 2018) and more recently in Carballal et al (2019b) or for microbiome analysis (Liu et al, 2017;Roguet et al, 2018), authentication of tequilas (Pérez-Caballero et al, 2017;Andrade et al, 2017), pathogenic point mutations (Rogers et al, 2018) or forensic identification (Gómez et al, 2018). Finally, with regard to the extraction of characteristics from images, some recently published works have been revised (Xu et al, 2018;Ali et al, 2016b;Wang et al, 2018;Sun et al, 2018;Zafar et al, 2018b).…”

Section: /20mentioning

confidence: 99%

Peer Review #3 of "Visual complexity modelling based on image features fusion of multiple kernels (v0.3)"

2019

View full text Add to dashboard Cite

Humans' perception of visual complexity is often regarded as one of the key principles of aesthetic order, and is intimately related to the physiological, neurological and, possibly, psychological characteristics of the human mind. For these reasons, creating accurate computational models of visual complexity is a demanding task. Building upon on previous work in the field Forsythe et al. (2011); Machado et al. (2015) we explore the use of Machine Learning techniques to create computational models of visual complexity. For that purpose, we use a dataset composed of 800 visual stimuli divided into five categories, describing each stimulus by 329 features based on edge detection, compression error and Zipf's law. In an initial stage, a comparative analysis of representative state-of-the-art Machine Learning approaches is performed. Subsequently, we conduct an exhaustive outlier analysis. We analyze the impact of removing the extreme outliers, concluding that Feature Selection Multiple Kernel Learning obtains the best results, yielding an average correlation to humans' perception of complexity of 0.71 with only twenty-two features. These results outperform the current state-of-the-art, showing the potential of this technique for regression.

show abstract

Fast object detection based on binary deep convolution neural networks

Cited by 35 publications

References 41 publications

Visual complexity modelling based on image features fusion of multiple kernels

Visual complexity modelling based on image features fusion of multiple kernels

An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks

Peer Review #3 of "Visual complexity modelling based on image features fusion of multiple kernels (v0.3)"

Contact Info

Product

Resources

About