LPNet: Retina Inspired Neural Network for Object Detection and Recognition

The detection of rotated objects is a meaningful and challenging research work. Although the state-of-the-art deep learning models have feature invariance, especially convolutional neural networks (CNNs), their architectures did not specifically design for rotation invariance. They only slightly com...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jie Cao, Chun Bao, Qun Hao, Yang Cheng, Chenglin Chen
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	convolutional neural networks LPNet retina-like log-polar object detection and recognition Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/22ae4392f2be4ce8bd028a5ec9a71afd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:22ae4392f2be4ce8bd028a5ec9a71afd
record_format	dspace
spelling	oai:doaj.org-article:22ae4392f2be4ce8bd028a5ec9a71afd2021-11-25T17:25:36ZLPNet: Retina Inspired Neural Network for Object Detection and Recognition10.3390/electronics102228832079-9292https://doaj.org/article/22ae4392f2be4ce8bd028a5ec9a71afd2021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2883https://doaj.org/toc/2079-9292The detection of rotated objects is a meaningful and challenging research work. Although the state-of-the-art deep learning models have feature invariance, especially convolutional neural networks (CNNs), their architectures did not specifically design for rotation invariance. They only slightly compensate for this feature through pooling layers. In this study, we propose a novel network, named LPNet, to solve the problem of object rotation. LPNet improves the detection accuracy by combining retina-like log-polar transformation. Furthermore, LPNet is a plug-and-play architecture for object detection and recognition. It consists of two parts, which we name as encoder and decoder. An encoder extracts images which feature in log-polar coordinates while a decoder eliminates image noise in cartesian coordinates. Moreover, according to the movement of center points, LPNet has stable and sliding modes. LPNet takes the single-shot multibox detector (SSD) network as the baseline network and the visual geometry group (VGG16) as the feature extraction backbone network. The experiment results show that, compared with conventional SSD networks, the mean average precision (mAP) of LPNet increased by 3.4% for regular objects and by 17.6% for rotated objects.Jie CaoChun BaoQun HaoYang ChengChenglin ChenMDPI AGarticleconvolutional neural networksLPNetretina-likelog-polarobject detection and recognitionElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2883, p 2883 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	convolutional neural networks LPNet retina-like log-polar object detection and recognition Electronics TK7800-8360
spellingShingle	convolutional neural networks LPNet retina-like log-polar object detection and recognition Electronics TK7800-8360 Jie Cao Chun Bao Qun Hao Yang Cheng Chenglin Chen LPNet: Retina Inspired Neural Network for Object Detection and Recognition
description	The detection of rotated objects is a meaningful and challenging research work. Although the state-of-the-art deep learning models have feature invariance, especially convolutional neural networks (CNNs), their architectures did not specifically design for rotation invariance. They only slightly compensate for this feature through pooling layers. In this study, we propose a novel network, named LPNet, to solve the problem of object rotation. LPNet improves the detection accuracy by combining retina-like log-polar transformation. Furthermore, LPNet is a plug-and-play architecture for object detection and recognition. It consists of two parts, which we name as encoder and decoder. An encoder extracts images which feature in log-polar coordinates while a decoder eliminates image noise in cartesian coordinates. Moreover, according to the movement of center points, LPNet has stable and sliding modes. LPNet takes the single-shot multibox detector (SSD) network as the baseline network and the visual geometry group (VGG16) as the feature extraction backbone network. The experiment results show that, compared with conventional SSD networks, the mean average precision (mAP) of LPNet increased by 3.4% for regular objects and by 17.6% for rotated objects.
format	article
author	Jie Cao Chun Bao Qun Hao Yang Cheng Chenglin Chen
author_facet	Jie Cao Chun Bao Qun Hao Yang Cheng Chenglin Chen
author_sort	Jie Cao
title	LPNet: Retina Inspired Neural Network for Object Detection and Recognition
title_short	LPNet: Retina Inspired Neural Network for Object Detection and Recognition
title_full	LPNet: Retina Inspired Neural Network for Object Detection and Recognition
title_fullStr	LPNet: Retina Inspired Neural Network for Object Detection and Recognition
title_full_unstemmed	LPNet: Retina Inspired Neural Network for Object Detection and Recognition
title_sort	lpnet: retina inspired neural network for object detection and recognition
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/22ae4392f2be4ce8bd028a5ec9a71afd
work_keys_str_mv	AT jiecao lpnetretinainspiredneuralnetworkforobjectdetectionandrecognition AT chunbao lpnetretinainspiredneuralnetworkforobjectdetectionandrecognition AT qunhao lpnetretinainspiredneuralnetworkforobjectdetectionandrecognition AT yangcheng lpnetretinainspiredneuralnetworkforobjectdetectionandrecognition AT chenglinchen lpnetretinainspiredneuralnetworkforobjectdetectionandrecognition
_version_	1718412336793911296

LPNet: Retina Inspired Neural Network for Object Detection and Recognition

Ejemplares similares