This research presents novel artificial vision techniques applied to the detection of features for strawberries used in the food industry. For this purpose, a computer vision system based in artificial neural networks is used, organized as a deep architecture and trained with noise compensated learning. This combination originates a strong network - object relations which makes possible the recognition of complex strawberry features under changing conditions of lightning, size and orientation. The programming uses OpenCV libraries and fruits databases captured with a webcam. The images used to train the Artificial Neural Network are defined with canny edge detection and a moving region of interest (ROI). After training, the network recognizes important features such as shape, color and anomalies. The system has been tested in real time with real images.
23 February 2017 in Journal of Artificial Intelligence and Soft Computing Research
This work proposes a deep neural net (DNN) that accomplishes the reliable visual recognition of a chosen object captured with a webcam and moving in a 3D space. Autoencoding and substitutional reality are used to train a shallow net until it achieves zero tracking error in a discrete ambient. This trained individual is set to work in a real world closed loop system where images coming from a webcam produce displacement information for a moving region of interest (ROI) inside the own image. This loop gives rise to an emergent tracking behavior which creates a self-maintain flow of compressed space-time data. Next, short term memory elements are set to play a key role by creating new representations in terms of a space-time matrix. The obtained representations are delivery as input to a second shallow network which acts as “recognizer”. A noise balanced learning method is used to fast train the recognizer with real-world images, giving rise to a simple and yet powerful robotic eye, with a slender neural processor that vigorously tracks and recognizes the chosen object. The system has been tested with real images in real time.
In this paper, we present a system for counting people on public transport. The system consists of a single camera, and it process videos obtained from the camcorder to perform an algorithm to identify and to count people using Artificial Neural Networks (ANNs). The system is implemented by Cpp language based on OpenCV. People counting is an important factor to guarantee safe road trips as transport vehicles must not exceed an established number of passengers. This research is aimed to create a technological tool that helps to comply with the Transit Law in Ecuador. We describe different processing blocks dedicated to the detection, segmentation, direction estimation, counting, and evaluation of images to present its results during the standard travel of a bus.
Engineering students majoring in instrumentation and control require training modules to realize practices in industrial processes and automatic control. Usually these modules are expensive and most are designed to control a single variable. In the present work we design and built a low-cost training module, which makes possible to realize labs practices in the industrial process control area, with up to two independent simultaneous variables, and by using modern elements. The system is easy to use, robust and has proved to be a useful tool for evaluating the different control modes required in the existent industrial world.
14 June 2019 in Smart Innovation, Systems and Technologies
This paper presents a industrial processes simulator compatible with PLC Siemens S7-1200 implemented in LabVIEW software, it consists of two industrial processes (mixer and control level), this system provides help on the practical learning of industrial automation by means of PLC, thanks to its ease of use and performance indicators and existing failures.