Object identification is a fundamental computer vision task with many real-world applications, from driverless vehicles to surveillance systems. In order to attain real-time performance, this work provides an effective method for object detection that makes use of cutting-edge deep learning algorithms. By combining a lightweight convolutional neural network architecture with cutting-edge optimization methods, our approach produces a model that maintains good accuracy while drastically decreasing computing complexity. We perform in-depth tests on well-known object detection datasets to confirm the viability of our method and show that it is faster and more accurate than other approaches. The proposed model lays the way for implementing object identification in resource-constrained settings where real-time responsiveness is crucial.
Article Details
Unique Paper ID: 161699
Publication Volume & Issue: Volume 10, Issue 5
Page(s): 414 - 417
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024