Real-time video event detection in crowded scenes using MPEG derived features : a multiple instance learning approach

This paper presents an investigation into event detection in crowded scenes, where the event of interest co-occurs with other activities and only binary labels at the clip level are available. The proposed approach incorporates a fast feature descriptor from the MPEG domain, and a novel multiple instance learning (MIL) algorithm using sparse approximation and random sensing. MPEG motion vectors are used to build particle trajectories that represent the motion of objects in uniform video clips, and the MPEG DCT coefficients are used to compute a foreground map to remove background particles. Trajectories are transformed into the Fourier domain, and the Fourier representations are quantized into visual words using the K-Means algorithm. The proposed MIL algorithm models the scene as a linear combination of independent events, where each event is a distribution of visual words. Experimental results show that the proposed approaches achieve promising results for event detection compared to the state-of-the-art.

An evaluation of different features and learning models for anomalous event detection

The huge amount of CCTV footage available makes it very burdensome to process these videos manually through human operators. This has made automated processing of video footage through computer vision technologies necessary. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned ‘normal’ model. There is no precise and exact definition for an abnormal activity; it is dependent on the context of the scene. Hence there is a requirement for different feature sets to detect different kinds of abnormal activities. In this work we evaluate the performance of different state of the art features to detect the presence of the abnormal objects in the scene. These include optical flow vectors to detect motion related anomalies, textures of optical flow and image textures to detect the presence of abnormal objects. These extracted features in different combinations are modeled using different state of the art models such as Gaussian mixture model(GMM) and Semi- 2D Hidden Markov model(HMM) to analyse the performances. Further we apply perspective normalization to the extracted features to compensate for perspective distortion due to the distance between the camera and objects of consideration. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.

Process model comprehension : the effects of cognitive abilities, learning style, and strategy

Process models are used to convey semantics about business operations that are to be supported by an information system. A wide variety of professionals is targeted to use such models, including people who have little modeling or domain expertise. We identify important user characteristics that influence the comprehension of process models. Through a free simulation experiment, we provide evidence that selected cognitive abilities, learning style, and learning strategy influence the development of process model comprehension. These insights draw attention to the importance of research that views process model comprehension as an emergent learning process rather than as an attribute of the models as objects. Based on our findings, we identify a set of organizational intervention strategies that can lead to more successful process modeling workshops.

Online self-supervised multi-instance segmentation of dynamic objects

This paper presents a method for the continuous segmentation of dynamic objects using only a vehicle mounted monocular camera without any prior knowledge of the object’s appearance. Prior work in online static/dynamic segmentation is extended to identify multiple instances of dynamic objects by introducing an unsupervised motion clustering step. These clusters are then used to update a multi-class classifier within a self-supervised framework. In contrast to many tracking-by-detection based methods, our system is able to detect dynamic objects without any prior knowledge of their visual appearance shape or location. Furthermore, the classifier is used to propagate labels of the same object in previous frames, which facilitates the continuous tracking of individual objects based on motion. The proposed system is evaluated using recall and false alarm metrics in addition to a new multi-instance labelled dataset to evaluate the performance of segmenting multiple instances of objects.

Intrinsic frames of reference in haptic spatial learning

It has been proposed that spatial reference frames with which object locations are specified in memory are intrinsic to a to-be-remembered spatial layout (intrinsic reference theory). Although this theory has been supported by accumulating evidence, it has only been collected from paradigms in which the entire spatial layout was simultaneously visible to observers. The present study was designed to examine the generality of the theory by investigating whether the geometric structure of a spatial layout (bilateral symmetry) influences selection of spatial reference frames when object locations are sequentially learned through haptic exploration. In two experiments, participants learned the spatial layout solely by touch and performed judgments of relative direction among objects using their spatial memories. Results indicated that the geometric structure can provide a spatial cue for establishing reference frames as long as it is accentuated by explicit instructions (Experiment 1) or alignment with an egocentric orientation (Experiment 2). These results are entirely consistent with those from previous studies in which spatial information was encoded through simultaneous viewing of all object locations, suggesting that the intrinsic reference theory is not specific to a type of spatial memory acquired by the particular learning method but instead generalizes to spatial memories learned through a variety of encoding conditions. In particular, the present findings suggest that spatial memories that follow the intrinsic reference theory function equivalently regardless of the modality in which spatial information is encoded.

Peripheral vision benefits spatial learning by guiding eye movements

The loss of peripheral vision impairs spatial learning and navigation. However, the mechanisms underlying these impairments remain poorly understood. One advantage of having peripheral vision is that objects in an environment are easily detected and readily foveated via eye movements. The present study examined this potential benefit of peripheral vision by investigating whether competent performance in spatial learning requires effective eye movements. In Experiment 1, participants learned room-sized spatial layouts with or without restriction on direct eye movements to objects. Eye movements were restricted by having participants view the objects through small apertures in front of their eyes. Results showed that impeding effective eye movements made subsequent retrieval of spatial memory slower and less accurate. The small apertures also occluded much of the environmental surroundings, but the importance of this kind of occlusion was ruled out in Experiment 2 by showing that participants exhibited intact learning of the same spatial layouts when luminescent objects were viewed in an otherwise dark room. Together, these findings suggest that one of the roles of peripheral vision in spatial learning is to guide eye movements, highlighting the importance of spatial information derived from eye movements for learning environmental layouts.

Sequential versus simultaneous viewing of an environment : effects of focal attention to individual object locations on visual spatial learning

We investigated memories of room-sized spatial layouts learned by sequentially or simultaneously viewing objects from a stationary position. In three experiments, sequential viewing (one or two objects at a time) yielded subsequent memory performance that was equivalent or superior to simultaneous viewing of all objects, even though sequential viewing lacked direct access to the entire layout. This finding was replicated by replacing sequential viewing with directed viewing in which all objects were presented simultaneously and participants’ attention was externally focused on each object sequentially, indicating that the advantage of sequential viewing over simultaneous viewing may have originated from focal attention to individual object locations. These results suggest that memory representation of object-to-object relations can be constructed efficiently by encoding each object location separately, when those locations are defined within a single spatial reference system. These findings highlight the importance of considering object presentation procedures when studying spatial learning mechanisms.

Path information effects in visual and proprioceptive spatial learning

Objects in an environment are often encountered sequentially during spatial learning, forming a path along which object locations are experienced. The present study investigated the effect of spatial information conveyed through the path in visual and proprioceptive learning of a room-sized spatial layout, exploring whether different modalities differentially depend on the integrity of the path. Learning object locations along a coherent path was compared with learning them in a spatially random manner. Path integrity had little effect on visual learning, whereas learning with the coherent path produced better memory performance than random order learning for proprioceptive learning. These results suggest that path information has differential effects in visual and proprioceptive spatial learning, perhaps due to a difference in the way one establishes a reference frame for representing relative locations of objects.

Learning from Eames : six lessons

"Eventually everything connects—people, ideas, objects. The quality of the connections is the key toquality per se.” (Charles Eames) On 8 November, 2007, in a moment charged with serendipity, an Exhibition titled ‘The Gifted Eye of Charles Eames—A Portfolio of 100 images’ was opened exclusively to Brisbane. The Artisan Gallery in Fortitude Valley became the launch point for an international orbit of Fringe locations hosting one of 18 sets of 100 images each...

Curiosity driven reinforcement learning for motion planning on humanoids

Most previous work on artificial curiosity (AC) and intrinsic motivation focuses on basic concepts and theory. Experimental results are generally limited to toy scenarios, such as navigation in a simulated maze, or control of a simple mechanical system with one or two degrees of freedom. To study AC in a more realistic setting, we embody a curious agent in the complex iCub humanoid robot. Our novel reinforcement learning (RL) framework consists of a state-of-the-art, low-level, reactive control layer, which controls the iCub while respecting constraints, and a high-level curious agent, which explores the iCub's state-action space through information gain maximization, learning a world model from experience, controlling the actual iCub hardware in real-time. To the best of our knowledge, this is the first ever embodied, curious agent for real-time motion planning on a humanoid. We demonstrate that it can learn compact Markov models to represent large regions of the iCub's configuration space, and that the iCub explores intelligently, showing interest in its physical constraints as well as in objects it finds in its environment.

The use of animation to promote student learning about the importance of mental well-being for tertiary study success

It is now widely acknowledged that student mental well-being is a critical factor in the tertiary student learning experience and is important to student learning success. The issue of student mental well-being also has implications for effective student transition out of university and into the world of work. It is therefore vital that intentional strategies are adopted by universities both within the formal curriculum, and outside it, to promote student well-being and to work proactively and preventatively to avoid a decline in student psychological well-being. This paper describes how the Queensland University of Technology Law School is using animation to teach students about the importance for their learning success of the protection of their mental well-being. Mayer and Moreno (2002) define an animation as an external representation with three main characteristics: (1) it is a pictorial representation, (2) it depicts apparent movement, and (3) it consists of objects that are artificially created through drawing or some other modelling technique. Research into the effectiveness of animation as a tool for tertiary student learning engagement is relatively new and growing field of enquiry. Nash argues, for example, that animations provide a “rich, immersive environment [that] encourages action and interactivity, which overcome an often dehumanizing learning management system approach” (Nash, 2009, 25). Nicholas states that contemporary millennial students in universities today, have been immersed in animated multimedia since their birth and in fact need multimedia to learn and communicate effectively (2008). However, it has also been established, for example through the work of Lowe (2003, 2004, 2008) that animations can place additional perceptual, attentional, and cognitive demands on students that they are not always equipped to cope with. There are many different genres of animation. The dominant style of animation used in the university learning environment is expository animation. This approach is a useful tool for visualising dynamic processes and is used to support student understanding of subjects and themes that might otherwise be perceived as theoretically difficult and disengaging. It is also a form of animation that can be constructed to avoid any potential negative impact on cognitive load that the animated genre might have. However, the nature of expository animation has limitations for engaging students, and can present as clinical and static. For this reason, the project applied Kombartzky, Ploetzner, Schlag, and Metz’s (2010) cognitive strategy for effective student learning from expository animation, and developed a hybrid form of animation that takes advantage of the best elements of expository animation techniques along with more engaging short narrative techniques. First, the paper examines the existing literature on the use of animation in tertiary educational contexts. Second, the paper describes how animation was used at QUT Law School to teach students about the issue of mental well-being and its importance to their learning success. Finally, the paper analyses the potential of the use of animation, and of the cognitive strategy and animation approach trialled in the project, as a teaching tool for the promotion of student learning about the importance of mental well-being.

The application of learning analytics to improve learning: Questions from the academy

Since 2007, close collaboration between the Learning and Teaching Unit’s Academic Quality and Standards team and the Department of Reporting and Analysis’ Business Objects team resulted in a generational approach to reporting where QUT established a place of trust. This place of trust is where data owners are confident in date storage, data integrity, reported and shared. While the role of the Department of Reporting and Analysis focused on the data warehouse, data security and publication of reports, the Academic Quality and Standards team focused on the application of learning analytics to solve academic research questions and improve student learning. Addressing questions such as: • Are all students who leave course ABC academically challenged? • Do the students who leave course XYZ stay within the faculty, university or leave? • When students withdraw from a unit do they stay enrolled on full or part load or leave? • If students enter through a particular pathway, what is their experience in comparison to other pathways? • With five years historic reporting, can a two-year predictive forecast provide any insight? In answering these questions, the Academic Quality and Standards team then developed prototype data visualisation through curriculum conversations with academic staff. Where these enquiries were applicable more broadly this information would be brought into the standardised reporting for the benefit of the whole institution. At QUT an annual report to the executive committees allows all stakeholders to record the performance and outcomes of all courses in a snapshot in time or use this live report at any point during the year. This approach to learning analytics was awarded the Awarded 2014 ATEM/Campus Review Best Practice Awards in Tertiary Education Management for The Unipromo Award for Excellence in Information Technology Management.