We tackle automatic meter reading (AMR) by leveraging the high capability of convolutional neural networks (CNNs). We design a two-stage approach that employs the Fast-YOLO object detector for counter detection and evaluates three different CNN-based approaches for counter recognition. In the AMR literature, most datasets are not available to the research community since the images belong to a service company. In this sense, we introduce a public dataset, called Federal University of Paraná-AMR dataset, with 2000 fully and manually annotated images. This dataset is, to the best of our knowledge, three times larger than the largest public dataset found in the literature and contains a well-defined evaluation protocol to assist the development and evaluation of AMR methods. Furthermore, we propose the use of a data augmentation technique to generate a balanced training set with many more examples to train the CNN models for counter recognition. In the proposed dataset, impressive results were obtained and a detailed speed/accuracy trade-off evaluation of each model was performed. In a public dataset, state-of-the-art results were achieved using <200 images for training.
KEYWORDS: Cameras, Data modeling, Imaging systems, Matrices, RGB color model, Machine vision, Computer vision technology, Simulation of CCA and DLA aggregates, Performance modeling, Surveillance
Person reidentification (Re-ID) aims at establishing global identities for individuals as they move across a camera network. It is a challenging task due to the drastic appearance changes that occur between cameras as a consequence of different pose and illumination conditions. Pairwise matching models yield state-of-the-art results in most of the person Re-ID datasets by capturing nuances that are robust and discriminative for a specific pair of cameras. Nonetheless, pairwise models are not scalable with the number of surveillance cameras. Therefore, elegant solutions combining scalability with high matching rates are crucial for the person Re-ID in real-world scenarios. We tackle this problem proposing a multicamera nonlinear regression model called kernel multiblock partial least squares (kernel MBPLS), a single subspace model for the entire camera network that uses all the labeled information. In this subspace, probe and gallery individual can be successfully matched. Experimental results in three multicamera person Re-ID datasets (WARD, RAiD, and SAIVT-SoftBIO) demonstrate that the kernel MBPLS presents favorable aspects, such as the scalability and robustness with respect to the number of cameras combined with the high matching rates.
In several image processing applications, discovering regions that have changed in a set of images acquired from a scene at different times and possibly from different viewpoints plays a very important role. Remote sensing, visual surveillance, medical diagnosis, civil infrastructure, and underwater sensing are examples of such applications that operate in dynamic environments. We propose an approach to detect such changes automatically by using image analysis techniques and segmentation based on superpixels in two stages: (1) the tuning stage, which is focused on adjusting the parameters; and (2) the unsupervised stage that is executed in real scenarios without an appropriate ground truth. Unlike most common approaches, which are pixel-based, our approach combines superpixel extraction, hierarchical clustering, and segment matching. Experimental results demonstrate the effectiveness of the proposed approach compared to a remote sensing technique and a background subtraction technique, demonstrating the robustness of our algorithm against illumination variations.
Robust local descriptors usually consist of high-dimensional feature vectors to describe distinctive characteristics of images. The high dimensionality of a feature vector incurs considerable costs in terms of computational time and storage. It also results in the curse of dimensionality that affects the performance of several tasks that use feature vectors, such as matching, retrieval, and classification of images. To address these problems, it is possible to employ some dimensionality reduction techniques, leading frequently to information lost and, consequently, accuracy reduction. This work aims at applying linear dimensionality reduction to the scale invariant feature transformation and speeded up robust feature descriptors. The objective is to demonstrate that even risking the decrease of the accuracy of the feature vectors, it results in a satisfactory trade-off between computational time and storage requirements. We perform linear dimensionality reduction through random projections, principal component analysis, linear discriminant analysis, and partial least squares in order to create lower dimensional feature vectors. These new reduced descriptors lead us to less computational time and memory storage requirements, even improving accuracy in some cases. We evaluate reduced feature vectors in a matching application, as well as their distinctiveness in image retrieval. Finally, we assess the computational time and storage requirements by comparing the original and the reduced feature vectors.
Successful execution of tasks such as image classification, object detection and recognition, and scene classification depends on the definition of a set of features able to describe images effectively. Texture is among the features used by the human visual system. It provides information regarding spatial distribution, changes in brightness, and description regarding the structural arrangement of surfaces. However, although the visual human system is extremely accurate to recognize and describe textures, it is difficult to define a set of textural descriptors to be used in image analysis on different application domains. This work evaluates several texture descriptors and demonstrates that the combination of descriptors can improve the performance of texture classification.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.