An Evaluation of RetinaNet on Indoor Object Detection for Blind and Visually Impaired Persons Assistance Navigation

Afif, Mouna; Ayachi, Riadh; Said, Yahia; Pissaloux, Edwige; Atri, Mohamed

doi:10.1007/s11063-020-10197-9

Cited by 81 publications

(41 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed algorithm is compared with other mainstream target detection algorithms in order to further verify the advantages of the proposed algorithm, as shown in Table 6 . The comparison algorithms include single-stage target detection algorithms SSD and RetinaNet [ 38 , 39 ] and double-stage target detection algorithm Cascade R-CNN [ 40 ].…”

Section: Steel Defect Detection Methodsmentioning

confidence: 99%

A New Steel Defect Detection Algorithm Based on Deep Learning

Zhao

Feng

Huang

et al. 2021

Computational Intelligence and Neuroscience

124

View full text Add to dashboard Cite

In recent years, more and more scholars devoted themselves to the research of the target detection algorithm due to the continuous development of deep learning. Among them, the detection and recognition of small and complex targets are still a problem to be solved. The authors of this article have understood the shortcomings of the deep learning detection algorithm in detecting small and complex defect targets and would like to share a new improved target detection algorithm in steel surface defect detection. The steel surface defects will affect the quality of steel seriously. We find that most of the current detection algorithms for NEU-DET dataset detection accuracy are low, so we choose to verify a steel surface defect detection algorithm based on machine vision on this dataset for the problem of defect detection in steel production. A series of improvement measures are carried out in the traditional Faster R-CNN algorithm, such as reconstructing the network structure of Faster R-CNN. Based on the small features of the target, we train the network with multiscale fusion. For the complex features of the target, we replace part of the conventional convolution network with a deformable convolution network. The experimental results show that the deep learning network model trained by the proposed method has good detection performance, and the mean average precision is 0.752, which is 0.128 higher than the original algorithm. Among them, the average precision of crazing, inclusion, patches, pitted surface, rolled in scale and scratches is 0.501, 0.791, 0.792, 0.874, 0.649, and 0.905, respectively. The detection method is able to identify small target defects on the steel surface effectively, which can provide a reference for the automatic detection of steel defects.

show abstract

Section: Steel Defect Detection Methodsmentioning

confidence: 99%

A New Steel Defect Detection Algorithm Based on Deep Learning

Zhao

Feng

Huang

et al. 2021

Computational Intelligence and Neuroscience

124

View full text Add to dashboard Cite

show abstract

“…The system uses Microsoft HoloLens to learn the geometry layout of the surroundings, which is necessary to plan feasible paths [11][12][13]. Edwige Pissaloux recently used a framework based on deep convolutional neural networks (Deep CNN) to detect indoor targets [14,15], an essential component for intelligence assistive systems. Cang Ye focused on guiding robots [16,17], while Bogdan Mocanu mainly studied mobile facial recognition, which is supposed to support the assistive system [18,19].…”

Section: Most Active and Influential Authors By Co-authorship And Co-citationshipmentioning

confidence: 99%

A Bibliometric Narrative Review on Modern Navigation Aids for People with Visual Impairment

et al. 2021

View full text Add to dashboard Cite

The innovations in the field of specialized navigation systems have become prominent research topics. As an applied science for people with special needs, navigation aids for the visually impaired are a key sociotechnique that helps users to independently navigate and access needed resources indoors and outdoors. This paper adopts the informetric analysis method to assess the current research and explore trends in navigation systems for the visually impaired based on bibliographic records retrieved from the Web of Science Core Collection (WoSCC). A total of 528 relevant publications from 2010 to 2020 were analyzed. This work answers the following questions: What are the publication characteristics and most influential publication sources? Who are the most active and influential authors? What are their research interests and primary contributions to society? What are the featured key studies in the field? What are the most popular topics and research trends, described by keywords? Additionally, we closely investigate renowned works that use different multisensor fusion methods, which are believed to be the bases of upcoming research. The key findings of this work aim to help upcoming researchers quickly move into the field, as they can easily grasp the frontiers and the trend of R&D in the research area. Moreover, we suggest the researchers embrace smartphone-based agile development, as well as pay more attention to phone-based prominent frameworks such as ARCore or ARKit, to achieve a fast prototyping for their proposed systems. This study also provides references for the associated fellows by highlighting the critical junctures of the modern assistive travel aids for people with visual impairments.

show abstract

“…Compared to other image-classification techniques such as Local Binary Patterns (LBP), Scale Invariant Feature Transform (SIFT), K-Nearest Neighbor (KNN) or Support Vector Machines (SVM), CNNs show better robustness when performing classification with large databases, achieving better accuracy in their results [ 2 , 3 , 4 ]. Therefore, CNNs have occupied a fundamental role in the development of different applications, such as video surveillance [ 5 ], autonomous and assisted driving [ 6 ], assistance navigation for blind and visually impaired people [ 7 ], detection of defects in structures [ 8 ], and clinical assistance [ 9 , 10 ]. CNNs perform image classification during inference, a process that depends on the architecture of the network and yields different results depending on the CNN type.…”

Section: Introductionmentioning

confidence: 99%

A Heterogeneous Hardware Accelerator for Image Classification in Embedded Systems

Pérez

Figueroa

2021

Sensors

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have been extensively employed for image classification due to their high accuracy. However, inference is a computationally-intensive process that often requires hardware acceleration to operate in real time. For mobile devices, the power consumption of graphics processors (GPUs) is frequently prohibitive, and field-programmable gate arrays (FPGA) become a solution to perform inference at high speed. Although previous works have implemented CNN inference on FPGAs, their high utilization of on-chip memory and arithmetic resources complicate their application on resource-constrained edge devices. In this paper, we present a scalable, low power, low resource-utilization accelerator architecture for inference on the MobileNet V2 CNN. The architecture uses a heterogeneous system with an embedded processor as the main controller, external memory to store network data, and dedicated hardware implemented on reconfigurable logic with a scalable number of processing elements (PE). Implemented on a XCZU7EV FPGA running at 200 MHz and using four PEs, the accelerator infers with 87% top-5 accuracy and processes an image of 224×224 pixels in 220 ms. It consumes 7.35 W of power and uses less than 30% of the logic and arithmetic resources used by other MobileNet FPGA accelerators.

show abstract

An Evaluation of RetinaNet on Indoor Object Detection for Blind and Visually Impaired Persons Assistance Navigation

Cited by 81 publications

References 35 publications

A New Steel Defect Detection Algorithm Based on Deep Learning

A New Steel Defect Detection Algorithm Based on Deep Learning

A Bibliometric Narrative Review on Modern Navigation Aids for People with Visual Impairment

A Heterogeneous Hardware Accelerator for Image Classification in Embedded Systems

Contact Info

Product

Resources

About