Audiovisual Tracking of Multiple Speakers in Smart Spaces.

This paper presents GAVT, a highly accurate audiovisual 3D tracking system based on particle filters and a probabilistic framework, employing a single camera and a microphone array. Our first contribution is a complex visual appearance model that accurately locates the speaker's mouth. It transforms a Viola & Jones face detector classifier kernel into a likelihood estimator, leveraging knowledge from multiple classifiers trained for different face poses. Additionally, we propose a mechanism to handle occlusions based on the new likelihood's dispersion. The audio localization proposal utilizes a probabilistic steered response power, representing cross-correlation functions as Gaussian mixture models. Moreover, to prevent tracker interference, we introduce a novel mechanism for associating Gaussians with speakers. The evaluation is carried out using the AV16.3 and CAV3D databases for Single- and Multiple-Object Tracking tasks (SOT and MOT, respectively). GAVT significantly improves the localization performance over audio-only and video-only modalities, with up to 50.3% average relative improvement in 3D when compared with the video-only modality. When compared to the state of the art, our audiovisual system achieves up to 69.7% average relative improvement for the SOT and MOT tasks in the AV16.3 dataset (2D comparison), and up to 18.1% average relative improvement in the MOT task for the CAV3D dataset (3D comparison).

Smart Video Surveillance System Based on Edge Computing.

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people's movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system.

Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild.

Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio-temporal features are extracted from each surveillance video using a temporal convolutional 3D neural network (T-C3D). Then, a novel ranking loss function increases the distance between the classification scores of anomalous and normal videos, reducing the number of false negatives. The proposal has been evaluated and compared against state-of-art approaches, obtaining competitive performance without fine-tuning, which also validates its generalization capability. In this paper, the proposal design and reliability is presented and analyzed, as well as the aforementioned quantitative and qualitative evaluation in-the-wild scenarios, demonstrating its high sensitivity in anomaly detection in all of them.

Headgear Accessories Classification Using an Overhead Depth Sensor.

In this paper, we address the generation of semantic labels describing the headgear accessories carried out by people in a scene under surveillance, only using depth information obtained from a Time-of-Flight (ToF) camera placed in an overhead position. We propose a new method for headgear accessories classification based on the design of a robust processing strategy that includes the estimation of a meaningful feature vector that provides the relevant information about the people's head and shoulder areas. This paper includes a detailed description of the proposed algorithmic approach, and the results obtained in tests with persons with and without headgear accessories, and with different types of hats and caps. In order to evaluate the proposal, a wide experimental validation has been carried out on a fully labeled database (that has been made available to the scientific community), including a broad variety of people and headgear accessories. For the validation, three different levels of detail have been defined, considering a different number of classes: the first level only includes two classes (hat/cap, and no hat/cap), the second one considers three classes (hat, cap and no hat/cap), and the last one includes the full class set with the five classes (no hat/cap, cap, small size hat, medium size hat, and large size hat). The achieved performance is satisfactory in every case: the average classification rates for the first level reaches 95.25%, for the second one is 92.34%, and for the full class set equals 84.60%. In addition, the online stage processing time is 5.75 ms per frame in a standard PC, thus allowing for real-time operation.

Filling the Gap between Research and Market: Portable Architecture for an Intelligent Autonomous Wheelchair.

Under the umbrella of assistive technologies research, a lot of different platforms have appeared since the 1980s, trying to improve the independence of people with severe mobility problems. Those works followed the same path coming from the field of robotics trying to reach users' needs. Nevertheless, those approaches rarely arrived on the market, due to their specificity and price. This paper presents a new prototype of an intelligent wheelchair (IW) that tries to fill the gap between research labs and market. In order to achieve such a goal, the proposed solution balances the criteria of performance and cost by using low-cost hardware and open software standards in mobile robots combined together within a modular architecture, which can be easily adapted to different profiles of a wide range of potential users. The basic building block consists of a mechanical chassis with two electric motors and a low-level electronic control system; driven by a joystick, this platform behaves similar to a standard electrical wheelchair. However, the underlying structure of the system includes several independent but connected nodes that form a distributed and scalable architecture that allows its adaptability, by adding new modules, to tackle autonomous navigation. The communication among the system nodes is based on the controller area network (CAN) specification, an extended standard in industrial fields that have a wide range of low-cost devices and tools. The system was tested and evaluated in indoor environments and by final users in order to ensure its usability, robustness, and reliability; it also demonstrated its functionality when navigating through buildings, corridors, and offices. The portability of the solution proposed is also shown by presenting the results on two different platforms: one for kids and another one for adults, based on different commercial mechanical platforms.

Effect of Carbamazepine, Ibuprofen, Triclosan and Sulfamethoxazole on Anaerobic Bioreactor Performance: Combining Cell Damage, Ecotoxicity and Chemical Information.

Pharmaceuticals and personal care products (PPCPs) are partially degraded in wastewater treatment plants (WWTPs), thereby leading to the formation of more toxic metabolites. Bacterial populations in bioreactors operated in WWTPs are sensitive to different toxics such as heavy metals and aromatic compounds, but there is still little information on the effect that pharmaceuticals exert on their metabolism, especially under anaerobic conditions. This work evaluated the effect of selected pharmaceuticals that remain in solution and attached to biosolids on the metabolism of anaerobic biomass. Batch reactors operated in parallel under the pressure of four individual and mixed PPCPs (carbamazepine, ibuprofen, triclosan and sulfametoxazole) allowed us to obtain relevant information on anaerobic digestion performance, toxicological effects and alterations to key enzymes involved in the biodegradation process. Cell viability was quantitatively evaluated using an automatic analysis of confocal microscopy images, and showed that triclosan and mixed pollutants caused higher toxicity and cell death than the other individual compounds. Both individual pollutants and their mixture had a considerable impact on the anaerobic digestion process, favoring carbon dioxide production, lowering organic matter removal and methane production, which also produced microbial stress and irreversible cell damage.

Odometry and laser scanner fusion based on a discrete extended Kalman Filter for robotic platooning guidance.

This paper describes a relative localization system used to achieve the navigation of a convoy of robotic units in indoor environments. This positioning system is carried out fusing two sensorial sources: (a) an odometric system and (b) a laser scanner together with artificial landmarks located on top of the units. The laser source allows one to compensate the cumulative error inherent to dead-reckoning; whereas the odometry source provides less pose uncertainty in short trajectories. A discrete Extended Kalman Filter, customized for this application, is used in order to accomplish this aim under real time constraints. Different experimental results with a convoy of Pioneer P3-DX units tracking non-linear trajectories are shown. The paper shows that a simple setup based on low cost laser range systems and robot built-in odometry sensors is able to give a high degree of robustness and accuracy to the relative localization problem of convoy units for indoor applications.

Stereo vision tracking of multiple objects in complex indoor environments.

This paper presents a novel system capable of solving the problem of tracking multiple targets in a crowded, complex and dynamic indoor environment, like those typical of mobile robot applications. The proposed solution is based on a stereo vision set in the acquisition step and a probabilistic algorithm in the obstacles position estimation process. The system obtains 3D position and speed information related to each object in the robot's environment; then it achieves a classification between building elements (ceiling, walls, columns and so on) and the rest of items in robot surroundings. All objects in robot surroundings, both dynamic and static, are considered to be obstacles but the structure of the environment itself. A combination of a Bayesian algorithm and a deterministic clustering process is used in order to obtain a multimodal representation of speed and position of detected obstacles. Performance of the final system has been tested against state of the art proposals; test results validate the authors' proposal. The designed algorithms and procedures provide a solution to those applications where similar multimodal data structures are found.