1,720,974 research outputs found
ODIN: An Object Detection and Instance Segmentation Diagnosis Framework
Full text linkObject detection and instance segmentation are major tasks in Computer Vision and have substantially progressed after the introduction of Deep Convolutional Neural Network (DCNN). Analyzing the performance of DCNNs is an open research issue, addressed with attention techniques that inspect the response of inner network layers to input stimuli. A complementary approach relies on the black-box diagnosis of errors, which exploits ad hoc metadata on the input data set and factors the performance into indicators sensible or impacted by specific facets of the input (e.g., object size, presence of occlusions, image acquisition conditions, etc.). In this paper we present an open source error diagnosis framework for object detection and instance segmentation that helps model developers to add meta-annotations to their data sets, to compute performance metrics split by meta-annotation values, and to visualize diagnosis reports. The framework accepts the popular PASCAL VOC and MS COCO input formats, is agnostic to the training platform, and can be extended with application- and domain-specific meta-annotations and metrics with almost no coding
Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
Full text linkIllegal landfills are uncontrolled disposals of waste that cause severe environmental and health risk. Discovering them as early as possible is of prominent importance for preventing hazards, such as fire pollution and leakage. Before the digital era, the only means to detect illegal waste dumps was the on site inspection of potentially suspicious sites, a procedure extremely costly and impossible to scale to a vast territory. With the advent of Earth observation technology, scanning the territory via aerial images has become possible. However, manual image interpretation remains a complex and time-consuming task that requires expert skill. Photo interpretation can be partially automated by embedding the expert knowledge within a data driven classifier trained with samples provided by human annotators. In this paper, the detection of illegal landfills is formulated as a multi-scale scene classification problem. Scene elements positioning and spatial relations constitute hints of the presence of illegal waste dumps. A dataset of ≈3000 images (20 cm resolution per pixel) was created with the help of expert photo interpreters. A combination of ResNet50 and Feature Pyramid Network (FPN) elements accounting for different object scales achieves 88% precision with an 87% of recall in a test area. The results proved the feasibility of applying convolutional neural networks for scene classification in this scenario to optimize the process of waste dumps detection
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Mountain summit detection with Deep Learning: evaluation and comparison with heuristic methods
No full textLandform detection and analysis from Digital Elevation Models (DEM) of the Earth has been boosted by the availability of high-quality public data sets. Current landform identification methods apply heuristic algorithms based on predefined landform features, fine tuned with parameters that may depend on the region of interest. In this paper, we investigate the use of Deep Learning (DL) models to identify mountain summits based on features learned from data examples. We train DL models with the coordinates of known summits found in public databases and apply the trained models to DEM data obtaining as output the coordinates of candidate summits. We introduce two formulations of summit recognition (as a classification or a segmentation task), describe the respective DL models, compare them with heuristic methods quantitatively, illustrate qualitatively their performances, and discuss the challenges of training DL methods for landform recognition with highly unbalanced and noisy data sets
ODIN TS: A Tool for the Black-Box Evaluation of Time Series Analytics
No full textThe increasing availability of time series datasets enabled by the diffusion of IoT architectures and the progress in the analysis of temporal data fostered by Deep Learning methods are boosting the interest in anomaly detection and predictive maintenance applications. The analysis of performance for these tasks relies on standard metrics applied to the entire dataset. Such indicators provide a global performance assessment but might not provide a deep understanding of the model weaknesses. A complementary diagnostic approach exploits error categorization and ad hoc visualizations. In this paper, we present ODIN TS, an open source diagnosis framework for time series analysis that lets developers compute performance metrics, disaggregated by different criteria, and visualize diagnosis reports. ODIN TS is agnostic to the training platform and can be extended with application- and domain-specific meta-annotations and metrics with almost no coding. We show ODIN TS at work through two time series analytics examples
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
On the Use of Class Activation Maps in Remote Sensing: the case of Illegal Landfills
No full textRemote sensing image scene classification consists of classifying images of the Earth surface into scene categories that represent different semantic ones based on the ground objects and their spatial arrangement. Finding the objects within a scene is not trivial, because they can appear in different sizes and mutual positions. An open issue in scene classification with CNNs is understating if the network prediction relies on the clues that human Earth Observation experts consider. A suitable approach for investigating the inference process of neural models relies on Class Activation Maps, which emphasize the areas of an image contributing the most to the classification. This work evaluates CAMs for different CNNs methods, in terms of their capacity to identify the objects that determine the classification of scenes for the illegal landfill detection. Quantitative and qualitative analyses show that ECA-Net has consistent performance across all metrics, resulting the most promising approach to obtain CNNs that focus on the most relevant points with the higher IoU. The illustrated analysis is a step towards the computer-aided study of the variations of scene elements positioning and spatial relations that constitute hints of the presence of illegal waste dumps and opens the way to the application of weakly supervised techniques for training detectors of illegal landfills in large scale remote sensing image repositories
Algorithms for mountain peaks discovery: A comparison
No full textAnalyzing digital data to identify and classify landforms is an important task, which can contribute to improve the availability and quality of public open source cartography and to develop novel applications for tourism and environment monitoring. In the literature, several heuristic algorithms are documented for identifying the features of mountain regions, most notably the coordinates of summits, from input data set, such as the Digital Elevation Model (DEM) of the Earth. Choosing the method to use for mountain peaks detection depends on the requirements of the application at hand, but the decision is helped also by the availability of rigorous comparison among the different methods. In this paper, we propose an approach for such a comparison and present the results obtained evaluating the best known methods form the literature in an area of Switzerland
- …
