The document summarizes a synopsis submitted for a degree in computer application that examines object detection using the YOLO algorithm in Python. It introduces object detection and how YOLO uses a single neural network to simultaneously predict bounding boxes and class probabilities for objects in an image. The proposed system aims to detect objects in images faster than existing methods like CNN, RCNN, and Faster RCNN, with higher accuracy using YOLOv8, localization, segmentation, and hardware including a Ryzen CPU, 16GB RAM, and Nvidia GPU.
The document summarizes a synopsis submitted for a degree in computer application that examines object detection using the YOLO algorithm in Python. It introduces object detection and how YOLO uses a single neural network to simultaneously predict bounding boxes and class probabilities for objects in an image. The proposed system aims to detect objects in images faster than existing methods like CNN, RCNN, and Faster RCNN, with higher accuracy using YOLOv8, localization, segmentation, and hardware including a Ryzen CPU, 16GB RAM, and Nvidia GPU.
The document summarizes a synopsis submitted for a degree in computer application that examines object detection using the YOLO algorithm in Python. It introduces object detection and how YOLO uses a single neural network to simultaneously predict bounding boxes and class probabilities for objects in an image. The proposed system aims to detect objects in images faster than existing methods like CNN, RCNN, and Faster RCNN, with higher accuracy using YOLOv8, localization, segmentation, and hardware including a Ryzen CPU, 16GB RAM, and Nvidia GPU.
The document summarizes a synopsis submitted for a degree in computer application that examines object detection using the YOLO algorithm in Python. It introduces object detection and how YOLO uses a single neural network to simultaneously predict bounding boxes and class probabilities for objects in an image. The proposed system aims to detect objects in images faster than existing methods like CNN, RCNN, and Faster RCNN, with higher accuracy using YOLOv8, localization, segmentation, and hardware including a Ryzen CPU, 16GB RAM, and Nvidia GPU.
Download as DOCX, PDF, TXT or read online from Scribd
Download as docx, pdf, or txt
You are on page 1/ 10
UNIVERSITY OF MYSORE
A Synopsis on
“Object Detection with Yolo using Python”
Submitted in partial fulfillment for the award of degree of Bachelor of Computer Application during the year 2023-24.
Submitted by
Tejas Kumar BS U01BP21S0040
Deepak K U01BP21S0027 Sagar M U01BP21S0025 Niranjan A.M U01BP21S0057
DEPARTMENT OF COMPUTER APPLICATION
GSSS SIMHA SUBBAMAHALAKSHMI FIRST GRADE COLLEGE
KRS Road, Metagalli, Mysore-570016
1 2 ABSTRACT
Efficient and accurate object detection has been an important topic in the advancement of computer vision systems. With the advancement of deep learning techniques, the accuracy for object detection has increased drastically. The project aims to incorporate state-of-the-art technique for object detection with the goal of achieving high accuracy with a real-time performance. A major challenge in many of the object detection systems is the dependency on other computer vision techniques for helping the deep learning based approach, which leads to slow and non-optimal performance.
3 INTRODUCTION
Object detection is a well-known computer technology connected with computer vision and image processing.With the advancement of deep learning techniques, the accuracy for object detection has increased drastically.It focuses on detecting objects or its instances of a certain class (such as humans, flowers, animals) in digital images and videos. There are various applications including face detection, character recognition, and vehicle counter.
YOLO which stands for “You Only Look Once” algorithm, which promotes an end-to-end neural network that simultaneously predicts bounding boxes and class probabilities, revolutionizes object identification. Unlike earlier object identification techniques that used classifiers for detection, this novel methodology takes a different approach.
4 Problem Statement
Many problems in computer vision were saturating on their accuracy before a decade. However, with the rise of deep learning techniques, the accuracy of these problems drastically improved. One of the major problem was that of image classification, which is need as predicting the class of the image. A slightly complicated problem is that of image localization, where the image contains a single object and the system should predict the class of the location of the object in the image (a bounding box around the object).
5 Applications
A well known application of object detection is face detection, that is used in almost all the mobile cameras. A more generalized (multi-class) application can be used in autonomous driving where a variety of objects need to be detected. Also it has a important role to play in surveillance systems. These systems can be integrated with other tasks such as pose estimation where the 1st stage in the pipeline is to detect the object, and then the second stage will be to estimate pose in the detected region
6 EXISITING SYSTEM
There is various real time object detection with output models using different algorithms like CNN, RCNN, Faster RCNN, YOLOv3 etc. The problem with these algorithms is less accuracy and real time speed of object detection is low.
PROPOSED SYSTEM The proposed system is to detect the image as fast as possible with the best accuracy of the object. Here we are using YOLO(You only look once) Algorithm to make it work fast ,it detects and identifies the object.
The following steps, we use for implementing object detection :
Yolo v8 Localisation Segmentaion With high accuracy
7 IMPLEMENTAION DETAILS SOFTWARE The project is implemented in python 3. ROBOFLOW was used for training the deep network and YOLOv8 was used for image pre-processing.
HARDWARE The system specifications on which the model is trained and evaluated are mentioned as follows: CPU - ryzen-7 3.60 GHz, RAM - 16 Gb, 4gbGPU - Nvidia Titan Xp grapic card.
8 CONCLUSION
In this paper, we proposed using a single neural network to detect objects using the YOLO algorithm. When applied to different domains and generalized from natural pictures, this algorithm performs better than other approaches. The algorithm is easy to create and can be trained on an entire image. Strategies for region proposals restrict the classifier to a specific region. The entire image is accessed by YOLO when predicting boundaries. Furthermore, it forecasts a decrease in false positives in background areas. Comparing to other classifier algorithms this algorithm is much more efficient and fastest algorithm to use in real time.
REFERENCES
[1] P. F. Felzenszwalb, R. B. 0Girshick, D. McAllester and D. Ramanan,0"Object Detection in
Discriminatively0Trained0Part-Based Models," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 9, pp. 1627-1645, Sept. 2016. [2] K. E. A. van0de Sande, J.0R. R. Uijlings, T.0Gevers0and A.0W. M. Smeulders, "Segmentation0a0selective search for the object recognition," 2011 International Conference on Computer Vision, Barcelona, 2011, pp. 1879-1886.0 [3] R. Girshick,0"Fast RCNN," 0IEEE0International0Conference0on0Computer0Vision (ICCV), Santiago,02015, pp.01440-1448. [4] D. Erhan, C. Szegedy, A. Toshev and D. Anguelov, "Scalable Object Detection Using Deep Neural Networks," 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, 2014, pp. 2155-2162.
