Real-Time Object Detection Using Yolo Algorithm for Blind People

Vision is one of the foremost necessary sense that human beings use to interact with the surrounding objects. There are more than 200 visually challenges people in this world and being visually challenged obstruct lots of daily activities. Hence it is very important for blind person to know what objects they are interacting with and understand their surroundings. In this project we have created a website, which help the blind people to identify different objects in the surrounding using YOLO V3 algorithm. This integrates different technologies to build a rich website which not only helps to recognize different object in the visually challenged persons surrounding in real time but also guides them through an audio output. YOLO (You Only Look at Once) algorithm is used for object detection and recognition. This algorithm gives very close accuracy for object detection in real time and studies have also proven the this algorithm is faster and better than other object detection algorithms.

Download Full-text

Electronic Eye for Blind People with Object Detection and Audio Output Using Image Processing

International Journal of Advanced Research in Science, Communication and Technology ◽

10.48175/ijarsct-1043 ◽

2021 ◽

pp. 403-406

Author(s):

Atharva Shewale ◽

Mrunalini Mahakalkar ◽

Vijay Pawar ◽

Yajan Bharad ◽

Dr. Shwetambari Chiwhane

Keyword(s):

Machine Learning ◽

Image Processing ◽

Object Detection ◽

Real Time ◽

Blind People ◽

Blind Person ◽

Great Problem ◽

Unknown Environment ◽

Audio Output ◽

Electronic Eye

One of the major issues faced by Blind people is detecting and recognizing an object. The objective of this project is to help the blind people because mobility of blind people is always a great problem. The mobility of blind people in unknown environment seems impossible without external help, because they don’t have any proper idea about their surroundings. So, we are developing a electronic eye which helps them to know about their surroundings and also guide them during travelling. Developing a system based on image processing using DNN algorithm which is able to labeling objects with the help of OpenCV and Tensor flow libraries and converting the labeled text in to speech and producing output in the form of audio to make the blind person aware of the object in front of him or her. The scope of this system is also measuring the distance of the object from the person and reporting the same Object detection using image processing and Machine Learning. It searches the object. We want to innovate our system the possibility of using the hearing sense to understand real time objects. For the security purpose track blind people in real time environment.

Download Full-text

Efficient final output feature map processing method supporting real-time object detection and recognition

2020 International SoC Design Conference (ISOCC) ◽

10.1109/isocc50952.2020.9333051 ◽

2020 ◽

Author(s):

Seong Bin Choi ◽

Sang-Seol Lee ◽

Jonghee Park ◽

Sung-Joon Jang ◽

Byung-Ho Choi

Keyword(s):

Object Detection ◽

Real Time ◽

Processing Method ◽

Feature Map ◽

Map Processing ◽

Final Output ◽

Detection And Recognition

Download Full-text

Field Assessment of Camera Based Drilling Dynamics

10.2118/204634-ms ◽

2021 ◽

Author(s):

Alexis Koulidis ◽

Mohamed Abdullatif ◽

Ahmed Galal Abdel-Kader ◽

Mohammed-ilies Ayachi ◽

Shehab Ahmed ◽

...

Keyword(s):

Neural Network ◽

Object Detection ◽

Real Time ◽

Tracking Algorithm ◽

Interest Points ◽

Stick Slip ◽

Detection Algorithms ◽

Point Tracking ◽

Surface Data ◽

Field Assessment

Abstract Surface data measurement and analysis are an established mean of detecting drillstring low-frequency torsional vibration or stick-slip. The industry has also developed models that link surface torque and downhole drill bit rotational speed. Cameras provide an alternative noninvasive approach to existing wired/wireless sensors used to gather such surface data. The results of a preliminary field assessment of drilling dynamics utilizing camera-based drillstring monitoring are presented in this work. Detection and timing of events from the video are performed using computer vision techniques and object detection algorithms. A real-time interest point tracker utilizing homography estimation and sparse optical flow point tracking is deployed. We use a fully convolutional deep neural network trained to detect interest points and compute their accompanying descriptors. The detected points and descriptors are matched across video sequences and used for drillstring rotation detection and speed estimation. When the drillstring's vibration is invisible to the naked eye, the point tracking algorithm is preceded with a motion amplification function based on another deep convolutional neural network. We have clearly demonstrated the potential of camera-based noninvasive approaches to surface drillstring dynamics data acquisition and analysis. Through the application of real-time object detection algorithms on rig video feed, surface events were detected and timed. We were also able to estimate drillstring rotary speed and motion profile. Torsional drillstring modes can be identified and correlated with drilling parameters and bottomhole assembly design. A novel vibration array sensing approach based on a multi-point tracking algorithm is also proposed. A vibration threshold setting was utilized to enable an additional motion amplification function providing seamless assessment for multi-scale vibration measurement. Cameras were typically devices to acquire images/videos for offline automated assessment (recently) or online manual monitoring (mainly), this work has shown how fog/edge computing makes it possible for these cameras to be "conscious" and "intelligent," hence play a critical role in automation/digitalization of drilling rigs. We showcase their preliminary application as drilling dynamics and rig operations sensors in this work. Cameras are an ideal sensor for a drilling environment since they can be installed anywhere on a rig to perform large-scale live video analytics on drilling processes.

Download Full-text

Prediction of Crime Scene Objects Using Deep Learning

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.37512 ◽

2021 ◽

Vol 9 (VIII) ◽

pp. 857-864

Author(s):

Vibhavari B Rao

Keyword(s):

Deep Learning ◽

Object Detection ◽

Computer Architecture ◽

Real Time ◽

Surveillance System ◽

Crime Scene ◽

Detection Model ◽

Detection Algorithms ◽

Performance Metric ◽

Smart Surveillance

The crime rates today can inevitably put a civilian's life in danger. While consistent efforts are being made to alleviate crime, there is also a dire need to create a smart and proactive surveillance system. Our project implements a smart surveillance system that would alert the authorities in real-time when a crime is being committed. During armed robberies and hostage situations, most often, the police cannot reach the place on time to prevent it from happening, owing to the lag in communication between the informants of the crime scene and the police. We propose an object detection model that implements deep learning algorithms to detect objects of violence such as pistols, knives, rifles from video surveillance footage, and in turn send real-time alerts to the authorities. There are a number of object detection algorithms being developed, each being evaluated under the performance metric mAP. On implementing Faster R-CNN with ResNet 101 architecture we found the mAP score to be about 91%. However, the downside to this is the excessive training and inferencing time it incurs. On the other hand, YOLOv5 architecture resulted in a model that performed very well in terms of speed. Its training speed was found to be 0.012 s / image during training but naturally, the accuracy was not as high as Faster R-CNN. With good computer architecture, it can run at about 40 fps. Thus, there is a tradeoff between speed and accuracy and it's important to strike a balance. We use transfer learning to improve accuracy by training the model on our custom dataset. This project can be deployed on any generic CCTV camera by setting up a live RTSP (real-time streaming protocol) and streaming the footage on a laptop or desktop where the deep learning model is being run.

Download Full-text