Successive efforts have processed the Advanced Very High Resolution Radiometer (AVHRR) sensor archive to produce Normalized Difference Vegetation Index (NDVI) datasets (i.e., PAL, FASIR, GIMMS, and ...LTDR) under different corrections and processing schemes. Since NDVI datasets are used to evaluate carbon gains, differences among them may affect nations' carbon budgets in meeting international targets (such as the Kyoto Protocol). This study addresses the consistency across AVHRR NDVI datasets in the Iberian Peninsula (Spain and Portugal) by evaluating whether their 1982-1999 NDVI trends show similar spatial patterns. Significant trends were calculated with the seasonal Mann-Kendall trend test and their spatial consistency with partial Mantel tests. Over 23% of the Peninsula (N, E, and central mountain ranges) showed positive and significant NDVI trends across the four datasets and an additional 18% across three datasets. In 20% of Iberia (SW quadrant), the four datasets exhibited an absence of significant trends and an additional 22% across three datasets. Significant NDVI decreases were scarce (croplands in the Guadalquivir and Segura basins, La Mancha plains, and Valencia). Spatial consistency of significant trends across at least three datasets was observed in 83% of the Peninsula, but it decreased to 47% when comparing across the four datasets. FASIR, PAL, and LTDR were the most spatially similar datasets, while GIMMS was the most different. The different performance of each AVHRR dataset to detect significant NDVI trends (e.g., LTDR detected greater significant trends (both positive and negative) and in 32% more pixels than GIMMS) has great implications to evaluate carbon budgets. The lack of spatial consistency across NDVI datasets derived from the same AVHRR sensor archive, makes it advisable to evaluate carbon gains trends using several satellite datasets and, whether possible, independent/additional data sources to contrast.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
The detection of critical infrastructures in large territories represented by aerial and satellite images is of high importance in several fields such as in security, anomaly detection, land use ...planning, and land use change detection. However, the detection of such infrastructures is complex as they have highly variable shapes and sizes, i.e., some infrastructures, such as electrical substations, are too small while others, such as airports, are too large. Besides, airports can have a surface area either small or too large with completely different shapes, which makes its correct detection challenging. As far as we know, these limitations have not been tackled yet in previous works. This article presents 1) a smart critical infrastructure (CI) dataset, named CI-dataset, organized into two scales, small and large scales critical infrastructures and 2) a two-level resolution-independent critical infrastructure detection (DetDSCI) methodology that first determines the spatial resolution of the input image using a classification model, then analyses the image using the appropriate detector for that spatial resolution. The present study targets two representative classes, airports and electrical substations. Our experiments show that DetDSCI methodology achieves up to 37.53% F1 improvement with respect to Faster R-CNN, one of the most influential detection models.
Current surveillance and control systems still require human supervision and intervention. This work presents a novel automatic handgun detection system in videos appropriate for both, surveillance ...and control purposes. We reformulate this detection problem into the problem of minimizing false positives and solve it by i) building the key training data-set guided by the results of a deep Convolutional Neural Networks (CNN) classifier and ii) assessing the best classification model under two approaches, the sliding window approach and region proposal approach. The most promising results are obtained by Faster R-CNN based model trained on our new database. The best detector shows a high potential even in low quality youtube videos and provides satisfactory results as automatic alarm system. Among 30 scenes, it successfully activates the alarm after five successive true positives in a time interval smaller than 0.2 s, in 27 scenes. We also define a new metric, Alarm Activation Time per Interval (AATpI), to assess the performance of a detection model as an automatic detection system in videos.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms ...that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Latent fingerprint identification is one of the most essential identification procedures in criminal investigations. Addressing this task is challenging as (i) it requires analyzing massive databases ...in reasonable periods and (ii) it is commonly solved by combining different methods with very complex data-dependencies, which make fully exploiting heterogeneous CPU-GPU systems very complex. Most efforts in this context focus on improving the accuracy of the approaches and neglect reducing the processing time. Indeed, the most accurate approach was designed for one single thread. This work introduces the fastest methodology for latent fingerprint identification maintaining high accuracy called Asynchronous processing for Latent Fingerprint Identification (ALFI). ALFI fully exploits all the resources of CPU-GPU systems using asynchronous processing and fine-coarse parallelism for analyzing massive databases. Our approach reduces idle times in processing and exploits the inherent parallelism of comparing latent fingerprints to fingerprint impressions. We analyzed the performance of ALFI on Linux and Windows operating systems using the well-known NIST/FVC databases. Experimental results reveal that ALFI is in average 22x faster than the state-of-the-art algorithm, reaching a value of 44.7x for the best-studied case.
There are several breast cancer datasets for building Computer Aided Diagnosis systems (CADs) using either deep learning or traditional models. However, most of these datasets impose various ...trade-offs on practitioners related to their availability or inner clinical value. Recently, a public dataset called BreakHis has been released to overcome these limitations. BreakHis is organized into four magnification levels, each image is labeled according to its main category (Benign/Malignant) and its subcategory (A/F/PT/TA/PC/DC/LC/MC). This organization allows practitioners to address this problem either as a binary or a multi-category classification task with either a magnification dependent or independent training approach. In this work, we define a taxonomy that categorize this problem into four different reformulations: Magnification-Specific Binary (MSB), Magnification-Independent Binary (MIB), Magnification-Specific Multi-category (MSM) and Magnification-Independent Multi-category (MIM) classifications. We provide a comprehensive survey of all related works. We identify the best reformulation from clinical and practical standpoints. Finally, we explore for the first time the MIM approach using deep learning and draw the learnt lessons.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
The capability of distinguishing between small objects when manipulated with hand is essential in many fields, especially in video surveillance. To date, the recognition of such objects in images ...using Convolutional Neural Networks (CNNs) remains a challenge. In this paper, we propose improving robustness, accuracy and reliability of the detection of small objects handled similarly using binarization techniques. We propose improving their detection in videos using a two level methodology based on deep learning, called Object Detection with Binary Classifiers. The first level selects the candidate regions from the input frame and the second level applies a binarization technique based on a CNN-classifier with One-Versus-All or One-Versus-One. In particular, we focus on the video surveillance problem of detecting weapons and objects that can be confused with a handgun or a knife when manipulated with hand. We create a database considering six objects: pistol, knife, smartphone, bill, purse and card. The experimental study shows that the proposed methodology reduces the number of false positives with respect to the baseline multi-class detection model.
•We propose and evaluate a two level methodology called ODeBiC, based on the use of deep learning, to improve the detection of small objects that can be handled similarly. The first level uses a detector to select from each input frame the candidate regions with a specific confidence about the presence of each object. Then, the second level analyses these proposals using a binarization technique to identify the objects with higher accuracy. ODeBiC methodology maintains a good accuracy for the detection of large objects as well.•We analyse the potential of binarization techniques such as, OVA and OVO, to improve the detection of small objects, manipulated with hand, that can be confused with a weapon. As far as we know, this is the first study in analysing such potential.•We build a new dataset called Sohas_weapon (small objects handled similarly to a weapon, dataset) for the case study of six small objects that are often handled in a similar way to a weapon: pistol, knife, smartphone, bill, purse and card. We used different camera and surveillance camera technologies to take the images. 10% of the images were downloaded from Internet. All these images were manually annotated for the detection task. This useful dataset will be available for other studies (http://sci2s.ugr.es/weapons-detection).
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Despite their interest and threat status, the number of whales in world's oceans remains highly uncertain. Whales detection is normally carried out from costly sighting surveys, acoustic surveys or ...through high-resolution images. Since deep convolutional neural networks (CNNs) are achieving great performance in several computer vision tasks, here we propose a robust and generalizable CNN-based system for automatically detecting and counting whales in satellite and aerial images based on open data and tools. In particular, we designed a two-step whale counting approach, where the first CNN finds the input images with whale presence, and the second CNN locates and counts each whale in those images. A test of the system on Google Earth images in ten global whale-watching hotspots achieved a performance (F1-measure) of 81% in detecting and 94% in counting whales. Combining these two steps increased accuracy by 36% compared to a baseline detection model alone. Applying this cost-effective method worldwide could contribute to the assessment of whale populations to guide conservation actions. Free and global access to high-resolution imagery for conservation purposes would boost this process.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
•We review concepts related to the explainability of AI methods (XAI).•We comprehensive analyze the XAI literature organized in two taxonomies.•We identify future research directions of the XAI ...field.•We discuss potential implications of XAI and privacy in data fusion contexts.•We identify Responsible AI as a concept promoting XAI and other AI principles in practical settings.
In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
It is unquestionable that time series forecasting is of paramount importance in many fields. The most used machine learning models to address time series forecasting tasks are Recurrent Neural ...Networks (RNNs). Typically, those models are built using one of the three most popular cells, ELMAN, Long–Short Term Memory (LSTM), or Gated Recurrent Unit (GRU) cells, each cell has a different structure and implies a different computational cost. However, it is not clear why and when to use each RNN-cell structure. Actually, there is no comprehensive characterization of all the possible time series behaviors and no guidance on what RNN cell structure is the most suitable for each behavior. The objective of this study is two-fold: it presents a comprehensive taxonomy of all possible time series behaviors (deterministic, random-walk, nonlinear, long-memory, and chaotic), and provides insights into the best RNN cell structure for each time series behavior. We conducted two experiments: (1) The first experiment evaluates and analyzes the role of each component in the LSTM-Vanilla cell by creating 11 variants based on one alteration in its basic architecture (removing, adding, or substituting one cell component). (2) The second experiment evaluates and analyzes the performance of 20 possible RNN-cell structures. To evaluate, compare, and select the best model, different statistical metrics were used: error-based metrics, information criterion-based metrics, naïve-based metric, and direction change-based metric. To further improve our confidence in the models’ interpretation and selection, Friedman Wilcoxon–Holm signed-rank test was used.
Our results advocate the usage and the exploration of the newly created RNN variant, named SLIM, in time series forecasting thanks to its high ability to accurately predict the different time series behaviors as well as its simple structural design that does not require expensive temporal and computing resources.
•A taxonomy of time series behaviors was proposed.•A taxonomy of Recurrent Neural Network (RNN) cell structures was proposed.•A set of 31 RNN cell structures was evaluated.•The utility of each component in the Long–Short Term Memory cell was evaluated.•The best cell structure for forecasting each time series behavior was provided.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP