A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of multi-objective optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, the utility of applying these techniques in the multi-objective multi-agent learning domain has not yet been thoroughly investigated. Agents learn the value of their decisions by linearly scalarizing their reward signals at the local level, while acceptable system wide behaviour results. However, the non-linear relationship between weighting parameters of the scalarization function and the learned policy makes the discovery of system wide trade-offs time consuming. Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup. The analysed approaches intelligently explore the weight-space in order to find a wider range of system trade-offs. In our second contribution, we propose a novel adaptive weight algorithm which interacts with the underlying local multi-objective solvers and allows for a better coverage of the Pareto front. Our third contribution is the experimental validation of our approach by learning bi-objective policies in self-organising smart camera networks. We note that our algorithm (i) explores the objective space faster on many problem instances, (ii) obtained solutions that exhibit a larger hypervolume, while (iii) acquiring a greater spread in the objective space.

Strumenti di guida ottica per un sistema di marcatura laser

Il percorso di tesi che ho intrapreso è stato svolto presso l'azienda Datalogic, con l'intento di integrare un sistema di visione ad un sistema di marcatura laser. L'utilizzo di questo potente strumento è però vincolato dalla particolare posizione fisica occupata, di volta in volta, dall'oggetto; per questo motivo viene fissato nella posizione desiderata, attraverso dime meccaniche. Fin ad ora si riteneva assolutamente necessaria la presenza di un operatore per il controllo del corretto posizionamento, tramite una simulazione della marcatura. Per ovviare a questo limite strutturale, Datalogic ha pensato di introdurre uno strumento di aiuto e di visione del processo: la camera. L'idea di base è stata quella di impiegare le moderne smart camera per individuare l'oggetto da marcare e rendere quindi il processo più automatico possibile. Per giungere a questo risultato è stato necessario effettuare una calibrazione del sistema totale: Camera più Laser. Il mio studio si è focalizzato quindi nel creare un eseguibile che aiutasse il cliente ad effettuare questa operazione nella maniera più semplice possibile. E' stato creato un eseguibile in C# che mettesse in comunicazione i due dispositivi ed eseguisse la calibrazione dei parametri intrinseci ed estrinseci. Il risultato finale ha permesso di avere il sistema di riferimento mondo della camera coincidente con quello del piano di marcatura del laser. Ne segue che al termine del processo di calibrazione se un oggetto verrà rilevato dalla camera, avente il baricentro nella posizione (10,10), il laser, utilizzando le medesime coordinate, marcherà proprio nel baricentro dell'oggetto desiderato. La maggiore difficoltà riscontrata è stata la differenza dei software che permettono la comunicazione con i due dispositivi e la creazione di una comunicazione con il laser, non esistente prima in C#.

PhD forum : multiple camera management using wide base-line matching

Manual calibration of large and dynamic networks of cameras is labour intensive and time consuming. This is a strong motivator for the development of automatic calibration methods. Automatic calibration relies on the ability to find correspondences between multiple views of the same scene. If the cameras are sparsely placed, this can be a very difficult task. This PhD project focuses on the further development of uncalibrated wide baseline matching techniques.

A suspicious behaviour detection using a context space model for smart surveillance systems

Video surveillance systems using Closed Circuit Television (CCTV) cameras, is one of the fastest growing areas in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. This work attempts to address these problems by proposing an automatic suspicious behaviour detection which utilises contextual information. The utilisation of contextual information is done via three main components: a context space model, a data stream clustering algorithm, and an inference algorithm. The utilisation of contextual information is still limited in the domain of suspicious behaviour detection. Furthermore, it is nearly impossible to correctly understand human behaviour without considering the context where it is observed. This work presents experiments using video feeds taken from CAVIAR dataset and a camera mounted on one of the buildings Z-Block) at the Queensland University of Technology, Australia. From these experiments, it is shown that by exploiting contextual information, the proposed system is able to make more accurate detections, especially of those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information gives critical feedback to the system designers to refine the system.

Testing the accuracy of luminance maps acquired by smart phone cameras

This paper looks at the accuracy of using the built-in camera of smart phones and free software as an economical way to quantify and analyse light exposure by producing luminance maps from High Dynamic Range (HDR) images. HDR images were captured with an Apple iPhone 4S to capture a wide variation of luminance within an indoor and outdoor scene. The HDR images were then processed using Photosphere software (Ward, 2010.) to produce luminance maps, where individual pixel values were compared with calibrated luminance meter readings. This comparison has shown an average luminance error of ~8% between the HDR image pixel values and luminance meter readings, when the range of luminances in the image is limited to approximately 1,500cd/m2.

A smart wireless inertial measurement unit system: simplifying & encouraging usage of WIMU technology

Wireless Inertial Measurement Units (WIMUs) combine motion sensing, processing & communications functionsin a single device. Data gathered using these sensors has the potential to be converted into high quality motion data. By outfitting a subject with multiple WIMUs full motion data can begathered. With a potential cost of ownership several orders of magnitude less than traditional camera based motion capture, WIMU systems have potential to be crucially important in supplementing or replacing traditional motion capture and opening up entirely new application areas and potential markets particularly in the rehabilitative, sports & at-home healthcarespaces. Currently WIMUs are underutilized in these areas. A major barrier to adoption is perceived complexity. Sample rates, sensor types & dynamic sensor ranges may need to be adjusted on multiple axes for each device depending on the scenario. As such we present an advanced WIMU in conjunction with a Smart WIMU system to simplify this aspect with 3 usage modes: Manual, Intelligent and Autonomous. Attendees will be able to compare the 3 different modes and see the effects of good andbad set-ups on the quality of data gathered in real time.

The smart vision local navigation aid for blind and visually impaired persons

The SmartVision prototype is a small, cheap and easily wearable navigation aid for blind and visually impaired persons. Its functionality addresses global navigation for guiding the user to some destiny, and local navigation for negotiating paths, sidewalks and corridors, with avoidance of static as well as moving obstacles. Local navigation applies to both in- and outdoor situations. In this article we focus on local navigation: the detection of path borders and obstacles in front of the user and just beyond the reach of the white cane, such that the user can be assisted in centering on the path and alerted to looming hazards. Using a stereo camera worn at chest height, a portable computer in a shoulder-strapped pouch or pocket and only one earphone or small speaker, the system is inconspicuous, it is no hindrence while walking with the cane, and it does not block normal surround sounds. The vision algorithms are optimised such that the system can work at a few frames per second.

Automatic Food Intake Assessment Using Camera Phones

Obesity is becoming an epidemic phenomenon in most developed countries. The fundamental cause of obesity and overweight is an energy imbalance between calories consumed and calories expended. It is essential to monitor everyday food intake for obesity prevention and management. Existing dietary assessment methods usually require manually recording and recall of food types and portions. Accuracy of the results largely relies on many uncertain factors such as user's memory, food knowledge, and portion estimations. As a result, the accuracy is often compromised. Accurate and convenient dietary assessment methods are still blank and needed in both population and research societies. In this thesis, an automatic food intake assessment method using cameras, inertial measurement units (IMUs) on smart phones was developed to help people foster a healthy life style. With this method, users use their smart phones before and after a meal to capture images or videos around the meal. The smart phone will recognize food items and calculate the volume of the food consumed and provide the results to users. The technical objective is to explore the feasibility of image based food recognition and image based volume estimation. This thesis comprises five publications that address four specific goals of this work: (1) to develop a prototype system with existing methods to review the literature methods, find their drawbacks and explore the feasibility to develop novel methods; (2) based on the prototype system, to investigate new food classification methods to improve the recognition accuracy to a field application level; (3) to design indexing methods for large-scale image database to facilitate the development of new food image recognition and retrieval algorithms; (4) to develop novel convenient and accurate food volume estimation methods using only smart phones with cameras and IMUs. A prototype system was implemented to review existing methods. Image feature detector and descriptor were developed and a nearest neighbor classifier were implemented to classify food items. A reedit card marker method was introduced for metric scale 3D reconstruction and volume calculation. To increase recognition accuracy, novel multi-view food recognition algorithms were developed to recognize regular shape food items. To further increase the accuracy and make the algorithm applicable to arbitrary food items, new food features, new classifiers were designed. The efficiency of the algorithm was increased by means of developing novel image indexing method in large-scale image database. Finally, the volume calculation was enhanced through reducing the marker and introducing IMUs. Sensor fusion technique to combine measurements from cameras and IMUs were explored to infer the metric scale of the 3D model as well as reduce noises from these sensors.

Portable 3D laser-camera calibration system with color fusion for SLAM

Nowadays, the use of RGB-D sensors have focused a lot of research in computer vision and robotics. These kinds of sensors, like Kinect, allow to obtain 3D data together with color information. However, their working range is limited to less than 10 meters, making them useless in some robotics applications, like outdoor mapping. In these environments, 3D lasers, working in ranges of 20-80 meters, are better. But 3D lasers do not usually provide color information. A simple 2D camera can be used to provide color information to the point cloud, but a calibration process between camera and laser must be done. In this paper we present a portable calibration system to calibrate any traditional camera with a 3D laser in order to assign color information to the 3D points obtained. Thus, we can use laser precision and simultaneously make use of color information. Unlike other techniques that make use of a three-dimensional body of known dimensions in the calibration process, this system is highly portable because it makes use of small catadioptrics that can be placed in a simple manner in the environment. We use our calibration system in a 3D mapping system, including Simultaneous Location and Mapping (SLAM), in order to get a 3D colored map which can be used in different tasks. We show that an additional problem arises: 2D cameras information is different when lighting conditions change. So when we merge 3D point clouds from two different views, several points in a given neighborhood could have different color information. A new method for color fusion is presented, obtaining correct colored maps. The system will be tested by applying it to 3D reconstruction.