Convolutional neural networks for computer vision-based detection and recognition of dumpsters
- PDF / 2,220,158 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 86 Downloads / 227 Views
(0123456789().,-volV)(0123456789().,-volV)
S.I. : IWINAC 2015
Convolutional neural networks for computer vision-based detection and recognition of dumpsters Iva´n Ramı´rez1 • Alfredo Cuesta-Infante1 • Juan J. Pantrigo1 • Antonio S. Montemayor1 • Jose´ Luis Moreno2 Valvanera Alonso2 • Gema Anguita2 • Luciano Palombarani2
•
Received: 12 September 2017 / Accepted: 21 February 2018 Ó The Natural Computing Applications Forum 2018
Abstract In this paper, we propose a twofold methodology for visual detection and recognition of different types of city dumpsters, with minimal human labeling of the image data set. Firstly, we carry out transfer learning by using Google Inception-v3 convolutional neural network, which is retrained with only a small subset of labeled images out of the whole data set. This first classifier is then improved with a semi-supervised learning based on retraining for two more rounds, each one increasing the number of labeled images but without human supervision. We compare our approach against both to a baseline case, with no incremental retraining, and the best case, assuming we had a fully labeled data set. We use a data set of 27,624 labeled images of dumpsters provided by Ecoembes, a Spanish nonprofit organization that cares for the environment through recycling and the eco-design of packaging in Spain. Such a data set presents a number of challenges. As in other outdoor visual tasks, there are occluding objects such as vehicles, pedestrians and street furniture, as well as other dumpsters whenever they are placed in groups. In addition, dumpsters have different degrees of deterioration which may affect their shape and color. Finally, 35% of the images are classified according to the capacity of the container, which contains a feature which is hard to assess in a snapshot. Since the data set is fully labeled, we can compare our approach both against a baseline case, doing only the transfer learning using a minimal set of labeled images, and against the best case, using all the labels. The experiments show that the proposed system provides an accuracy of 88%, whereas in the best case it is 93%. In other words, the method proposed attains 94% of the best performance. Keywords Deep learning Dumpsters Semi-supervised learning Transfer learning
1 Introduction
& Alfredo Cuesta-Infante [email protected] Iva´n Ramı´rez [email protected] Juan J. Pantrigo [email protected] Antonio S. Montemayor [email protected] 1
School of Computer Science, Universidad Rey Juan Carlos, Mo´stoles, Madrid, Spain
2
Direccio´n Te´cnica e Innovacio´n & Direccio´n de RSC y Sistemas, Ecoembalajes Espan˜a, S.A. (ECOEMBES), Madrid, Spain
In the last 5 years, computer vision has experienced an outstanding revolution, mainly due to three factors. Firstly, there are inexpensive parallel computing platforms such as GPUs and other hardware accelerators (locally), and clusters of computers and cloud computing (online). Secondly, there are fast and inexpensive devices that can store huge volumes of lab
Data Loading...
