An Object Detection Technique For Blind People in Real-Time Using Deep Neural Network

Kumar, Ashwani; Reddy, Sreedhar; Kulkarni, Vivek

doi:10.1109/iciip47207.2019.8985965

Cited by 43 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing the YOLO approach to other object identification algorithms reveals a number of its benefits. In contrast to other algorithms, YOLO looks at the image completely by predicting the bounding boxes using convolutional networks, finding class probabilities for these boxes, and detecting the image more quickly than other algorithms like Convolutional Neural Network (CNN) and Fast-According to [10] a real-time object detection method enabling blind users to find things on any device running this model. To create the suggested model, we combine a convolutional neural network with a single shot multibox detection technique.…”

Section: Literature Surveymentioning

confidence: 99%

Real Time Object Detection System for Blind People

2023

IRJMETS

View full text Add to dashboard Cite

The human visual system is quick and precise, capable of carrying out complex tasks like distinguishing between many objects and accurately detecting impediments. Humans can also quickly recognize and locate items in their environment or a picture. Thanks to the web and computer vision technology advancements, we can now use machines to quickly and accurately identify items in photos and videos. The same technology assists visually impaired people in their everyday activities. Considering how closely object identification relates to video analysis and visual comprehension, it has received a lot of study interest lately. The foundation of conventional object identification techniques is shallow trainable structures and handmade features. Building intricate ensembles incorporating several low-level picture characteristics with high-level context from object detectors and scene classifiers may stabilize their performance. More potent tools that can learn semantic, high-level, deeper features are being offered to solve the issues with conventional architectures due to deep learning's fast growth. This study presented an intelligent object detection system based on Convolutional Neural Network (CNN) to give visually impaired persons a smart and secure way of life. The edge box technique was used to create region suggestions from each image's edge maps to lessen the complexity burden. The ideas were then put through a refined CaffeNet model. The camera caught the object scene in realtime, and the image's feature was retrieved. After that, an audio-based detector was created on the discovered item to alert those with visual impairments to the found thing.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Real Time Object Detection System for Blind People

2023

IRJMETS

View full text Add to dashboard Cite

show abstract

“…In fast RCNN, Ren et al [12] has used 16 architectures in convolution layers to achieve detection and classification accuracy on datasets. Kumar et al [30][31][32] proposed a method to detect the objects with audio device in real time for blind people using deep neural network. Figure 1 demonstrates the architecture of Faster RCNN.…”

Section: Faster Rcnnmentioning

confidence: 99%

Object detection in real time based on improved single shot multi-box detector algorithm

Kumar¹,

Zhang

Lyu

2020

J Wireless Com Network

Self Cite

119

View full text Add to dashboard Cite

In today’s scenario, the fastest algorithm which uses a single layer of convolutional network to detect the objects from the image is single shot multi-box detector (SSD) algorithm. This paper studies object detection techniques to detect objects in real time on any device running the proposed model in any environment. In this paper, we have increased the classification accuracy of detecting objects by improving the SSD algorithm while keeping the speed constant. These improvements have been done in their convolutional layers, by using depth-wise separable convolution along with spatial separable convolutions generally called multilayer convolutional neural networks. The proposed method uses these multilayer convolutional neural networks to develop a system model which consists of multilayers to classify the given objects into any of the defined classes. The schemes then use multiple images and detect the objects from these images, labeling them with their respective class label. To speed up the computational performance, the proposed algorithm is applied along with the multilayer convolutional neural network which uses a larger number of default boxes and results in more accurate detection. The accuracy in detecting the objects is checked by different parameters such as loss function, frames per second (FPS), mean average precision (mAP), and aspect ratio. Experimental results confirm that our proposed improved SSD algorithm has high accuracy.

show abstract

“…With the rapid development of artificial intelligence and advanced sensing technology, the use of deep learning to assist visually impaired people is booming. In recent years, there has been lots of work using deep learning to help visually impaired people perceive the environment and avoid obstacles (Poggi and Mattoccia 2016;Liu et al 2021;Kumar et al 2019). However, to our knowledge, research on deep learning based educational assistance systems targeted at visually impaired people is insufficient.…”

Section: Introductionmentioning

confidence: 99%

AviPer: assisting visually impaired people to perceive the world with visual-tactile multimodal attention network

Huang

et al. 2022

CCF Trans. Pervasive Comp. Interact.

View full text Add to dashboard Cite

Unlike able-bodied persons, it is difficult for visually impaired people, especially those in the educational age, to build a full perception of the world due to the lack of normal vision. The rapid development of AI and sensing technologies has provided new solutions to visually impaired assistance. However, to our knowledge, most previous studies focused on obstacle avoidance and environmental perception but paid less attention to educational assistance for visually impaired people. In this paper, we propose AviPer, a system that aims to assist visually impaired people to perceive the world via creating a continuous, immersive, and educational assisting pattern. Equipped with a self-developed flexible tactile glove and a webcam, AviPer can simultaneously predict the grasping object and provide voice feedback using the vision-tactile fusion classification model, when a visually impaired people is perceiving the object with his gloved hand. To achieve accurate multimodal classification, we creatively embed three attention mechanisms, namely temporal, channel-wise, and spatial attention in the model. Experimental results show that AviPer can achieve an accuracy of 99.75% in classification of 10 daily objects. We evaluated the system in a variety of extreme cases, which verified its robustness and demonstrated the necessity of visual and tactile modal fusion. We also conducted tests in the actual use scene and proved the usability and user-friendliness of the system. We opensourced the code and self-collected datasets in the hope of promoting research development and bringing changes to the lives of visually impaired people.

show abstract

An Object Detection Technique For Blind People in Real-Time Using Deep Neural Network

Cited by 43 publications

References 16 publications

Real Time Object Detection System for Blind People

Real Time Object Detection System for Blind People

Object detection in real time based on improved single shot multi-box detector algorithm

AviPer: assisting visually impaired people to perceive the world with visual-tactile multimodal attention network

Contact Info

Product

Resources

About