Instituto de Telecomunicações

Funder

Organizational Unit

Publications

Detection of waste containers using computer vision

Publication . Valente, Miguel; Silva, Hélio; Caldeira, J.M.L.P.; Soares, V.N.G.J.; Gaspar, Pedro Dinis

This work is a part of an ongoing study to substitute the identification of waste containers via radio-frequency identification. The purpose of this paper is to propose a method of identification based on computer vision that performs detection using images, video, or real-time video capture to identify different types of waste containers. Compared to the current method of identification, this approach is more agile and does not require as many resources. Two approaches are employed, one using feature detectors/descriptors and other using convolutional neural networks. The former used a vector of locally aggregated descriptors (VLAD); however, it failed to accomplish what was desired. The latter used you only look once (YOLO), a convolutional neural network, and reached an accuracy in the range of 90%, meaning that it correctly identified and classified 90% of the pictures used on the test set.

2019Journal article

Open access

Smartphone-based automatic measurement of the results of the timed-up and go test

Publication . Ponciano, Vasco Rafael Gaspar; Pires, Ivan M.; Ribeiro, Fernando Reinaldo; Garcia, Nuno M.; Pombo, Nuno; Spinsante, Susanna; Crisóstomo, Rute

The Timed-Up and Go test is a very used test in the physiotherapy area. For the measurement of the results of the test, we propose to use a smartphone with several embedded sensors, including accelerometer, magnetometer, gyroscope, a Bitalino device with the Electromyography (EMG) and Electrocardiography (ECG) sensors, and a second Bitalino device with a pressure sensor connected and positioned in the back of the chair. This architecture allows to capture several types of data from the sensors easily. In this paper, we present a structured method to implement the measurement of the different parameters involved in the Timed-up and Go test, for acquiring, processing and cleaning the collected measurements. This data will help in the classification of the test results initially, and later on to discover more complex patterns and related conditions, such as equilibrium changes, neurological pathologies, degenerative pathologies, lesions of lower limbs and chronic venous diseases.

2019Journal article

Restricted access

A new approach towards waste container detection in smart cities

Publication . Valente, Miguel; Caldeira, J.M.L.P.; Soares, V.N.G.J.; Silva, Hélio; Gaspar, Pedro Dinis

This paper presents a new approach to help redesigning waste management for the cities of the future. The current state of tracking waste containers is rigid, inefficient and hard to oversee. Although attempts have been made in the past using radio-frequency identification for waste container detection, it has shown problems like flexibility, cost and environmental impact. We propose and demonstrate a solution based on the use of computer vision techniques, for object detection and classification, towards the differentiation between different types of waste containers.

2019.Journal article

Open access