Abstract:
Efficient and accurate object detection has been an important topic in the
advancement of computer vision systems. With the advent of deep learning
techniques, the accuracy for object detection has increased drastically. The project
aims to incorporate neural networks technique for object detection with the goal of
achieving high accuracy with a real-time performance. Robotic vision continues to be
treated including different methods for processing, analyzing, and understanding. All
these methods produce information that is translated into decisions for robots. From
start to capture images and to the final decision of the robot, a wide range of
technologies and algorithms are used like a committee of filtering and decisions. This
report aims to design and implement the object detection and machine interfacing for
cockroach detection. Here the working procedure has been divided into two parts
hardware and software. In order for the system to be operational, Tensor flow,
Arduino and Raspberry Pi microcontroller as well as camera module has been used.
The projected algorithm has been used to train neural network model to detect
cockroach from picture and real time image which is captured by camera module as
input for finding accuracy. Finally, it is found that our project provides faster image
detection process.
