An Obstacle Detection Method for Visually Impaired Persons by Ground Plane Removal Using Speeded-Up Robust Features and Gray Level Co-Occurrence Matrix

Jindal, Anish; Aggarwal, Naveen; Gupta, Savita

doi:10.1134/s1054661818020086

Cited by 18 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jindal et al [27] have designed a novel smartphone-based cost-effective system for safe walking along the roads by observing the obstacles along the paths of the visually impaired people in real-time scenarios. The video was captured with the aid of the Monocular vision approach and they have extracted the frames from the video by the meaning of neglecting the blurriness that occurred in the image due to the camera motion.…”

Section: Related Workmentioning

confidence: 99%

A Novel Approach for Object Detection Using Optimized Convolutional Neural Network to Assist Visually Impaired People

Pardeshi¹,

Wagh²,

Kharat³

et al. 2023

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

Human race is blessed with the five basic senses such as touch, taste, smell, hearing and the most important of them all 'vision or eyesight'. It is very difficult to survive without any one of them. Unfortunately a mass population across the globe suffers from the ill effects of vision, hampering their daily life. Detecting objects and providing navigational instructions in an indoor environment can considerably improve the day-to-day quality of life of visually impaired people. The motive of this research work is to propose a solution approach for assisting visually impaired population by identifying obstacles in front of them considering indoor environment. This approach focuses on feature extraction and object detection using Convolutional Neural Network (CNN) from a real time video. For this a head mounted image acquisition device may be used to detect the objects from the scene ahead and information of the detected objects is provided to the visually impaired (VI) person through the audio modality. As a first step towards the overall conceptual process, an object detection system is presented in this article, which processes the live video stream captured through the acquisition device. The video is processed frame-by-frame, treating each frame as a separate image and then using the proposed feature extraction and object detection algorithm to identify the objects.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Approach for Object Detection Using Optimized Convolutional Neural Network to Assist Visually Impaired People

Pardeshi¹,

Wagh²,

Kharat³

et al. 2023

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

show abstract

“…Some are designed for specific applications (e.g., obstacles on the road for vehicle collision avoidance), others fuse multiple sensor modalities (which requires much more data and processing time), and yet others employ neural networks trained on specific types of obstacles. For example, two widely used methods, gray-level co-occurrence matrices (Jindal, Aggarwal, and Gupta 2018) and k-mean clustering (Kanungo et al 2002), proved to be far too computationally or logistically complex for the intended application. In addition, none of these methods quantify a degree of assurance that the detected anomaly is actually present as opposed to being a natural part of the scene.…”

Section: Approachmentioning

confidence: 99%

Obstacle detection and quantification for vehicle mobility in winter conditions

Vecherin¹,

Shaker²,

Parker³

2020

View full text Add to dashboard Cite

Recently, the focus for military operations has shifted from the desert to cold climates, causing a corresponding shift in the military's need to better understand the mobility of our current vehicle fleet in these areas. Therefore, this work investigated the effects of winter conditions on military vehicle mobility. The main objective was to detect obstacles on the scene. This study developed and tested a method for automatic obstacle detection in the digital elevation model of a scene. The method detects statistical anomalies relative to an estimated background image that contains no obstacles. The sensitivity of the detection can be adjusted by a specified probability of false alarms, and the obstacle detection confidence is characterized by a probability of detection. The visible height of obstacles above the snow is related to the actual height of the obstacles above the ground. Compared to other detection techniques, the developed method is fast, calibrates itself to the cluttered images, operates with a single given image, and aligns with a detection quantification adopted in the receiver operating characteristic framework. The examples considered in this paper demonstrate high efficiency and applicability of the developed approach to the military vehicle mobility missions.

show abstract

“…A reference image that its distance to the input image is smaller than the threshold is acceptable. Such ANN algorithms terminate when an acceptable reference image is found and decide that the class of the input image is same as the class of this 9 Directed Enumeration Method 10 Histogram of Oriented Gradients acceptable reference image. So the termination condition for these algorithms can be formulated as follows [3]:…”

Section: Ml-ann Algorithmmentioning

confidence: 99%

“…[3] In face recognition and generally image recognition problems, this process is more challenging due to the effect of lighting and complex background variability [5] and also variability of objects presented in images [4]. There are many ways for feature extraction such as "SIFT 1 " [6] which was applied in [7], "SURF 2 " [8] applied in [9], and "HOG 3 " [10] applied in [11].Based on the application, we can decide which one to use. After extracting the feature of all images, it is time to use machine learning algorithms [3] to classify the input image.…”

Section: Introductionmentioning

confidence: 99%

A Distributed Approximate Nearest Neighbor Method for Real-Time Face Recognition

Aghazadeh¹,

Amirmazlaghani²

2020

Preprint

View full text Add to dashboard Cite

Nowadays face recognition and more generally, image recognition have many applications in the modern world and are widely used in our daily tasks. In this paper, we propose a novel distributed approximate nearest neighbor (ANN) method for real-time face recognition with a big data-set that involves a lot of classes. The proposed approach is based on using a clustering method to separate the data-set into different clusters, and specifying the importance of each cluster by defining cluster weights. Reference instances are selected from each cluster based on the cluster weights and by using a maximum likelihood approach. This process leads to a more informed selection of instances, and so enhances the performance of the algorithm. Experimental results confirm the efficiency of the proposed method and its out-performance in terms of accuracy and processing time.

show abstract

An Obstacle Detection Method for Visually Impaired Persons by Ground Plane Removal Using Speeded-Up Robust Features and Gray Level Co-Occurrence Matrix

Cited by 18 publications

References 24 publications

A Novel Approach for Object Detection Using Optimized Convolutional Neural Network to Assist Visually Impaired People

A Novel Approach for Object Detection Using Optimized Convolutional Neural Network to Assist Visually Impaired People

Obstacle detection and quantification for vehicle mobility in winter conditions

A Distributed Approximate Nearest Neighbor Method for Real-Time Face Recognition

Contact Info

Product

Resources

About