Extending visual perception with haptic exploration for improved scene understanding

Scene understanding has been investigated from a mainly visual information point of view. Recently depth has been provided an extra wealth of information, allowing more geometric knowledge to fuse into scene understanding. Yet to form a holistic view, especially in robotic applications, one can create even more data by interacting with the world. In fact humans, when growing up, seem to heavily investigate the world around them by haptic exploration. We show an application of haptic exploration on a humanoid robot in cooperation with a learning method for object segmentation. The actions performed consecutively improve the segmentation of objects in the scene.

Deeper and wider fully convolutional network coupled with conditional random fields for scene labeling

Deep convolutional neural networks (DCNNs) have been employed in many computer vision tasks with great success due to their robustness in feature learning. One of the advantages of DCNNs is their representation robustness to object locations, which is useful for object recognition tasks. However, this also discards spatial information, which is useful when dealing with topological information of the image (e.g. scene labeling, face recognition). In this paper, we propose a deeper and wider network architecture to tackle the scene labeling task. The depth is achieved by incorporating predictions from multiple early layers of the DCNN. The width is achieved by combining multiple outputs of the network. We then further refine the parsing task by adopting graphical models (GMs) as a post-processing step to incorporate spatial and contextual information into the network. The new strategy for a deeper, wider convolutional network coupled with graphical models has shown promising results on the PASCAL-Context dataset.

Semi-binary based video features for activity representation

Efficient and effective feature detection and representation is an important consideration when processing videos, and a large number of applications such as motion analysis, 3D scene understanding, tracking etc. depend on this. Amongst several feature description methods, local features are becoming increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational complexity, their performance is still too limited for real world applications. Furthermore, rapid increases in the uptake of mobile devices has increased the demand for algorithms that can run with reduced memory and computational requirements. In this paper we propose a semi binary based feature detectordescriptor based on the BRISK detector, which can detect and represent videos with significantly reduced computational requirements, while achieving comparable performance to the state of the art spatio-temporal feature descriptors. First, the BRISK feature detector is applied on a frame by frame basis to detect interest points, then the detected key points are compared against consecutive frames for significant motion. Key points with significant motion are encoded with the BRISK descriptor in the spatial domain and Motion Boundary Histogram in the temporal domain. This descriptor is not only lightweight but also has lower memory requirements because of the binary nature of the BRISK descriptor, allowing the possibility of applications using hand held devices.We evaluate the combination of detectordescriptor performance in the context of action classification with a standard, popular bag-of-features with SVM framework. Experiments are carried out on two popular datasets with varying complexity and we demonstrate comparable performance with other descriptors with reduced computational complexity.

Improving deep convultional neural networks with unsupervised feature learning

The latest generation of Deep Convolutional Neural Networks (DCNN) have dramatically advanced challenging computer vision tasks, especially in object detection and object classification, achieving state-of-the-art performance in several computer vision tasks including text recognition, sign recognition, face recognition and scene understanding. The depth of these supervised networks has enabled learning deeper and hierarchical representation of features. In parallel, unsupervised deep learning such as Convolutional Deep Belief Network (CDBN) has also achieved state-of-the-art in many computer vision tasks. However, there is very limited research on jointly exploiting the strength of these two approaches. In this paper, we investigate the learning capability of both methods. We compare the output of individual layers and show that many learnt filters and outputs of the corresponding level layer are almost similar for both approaches. Stacking the DCNN on top of unsupervised layers or replacing layers in the DCNN with the corresponding learnt layers in the CDBN can improve the recognition/classification accuracy and training computational expense. We demonstrate the validity of the proposal on ImageNet dataset.

Multiple instance dictionary learning for activity representation

This paper presents an effective feature representation method in the context of activity recognition. Efficient and effective feature representation plays a crucial role not only in activity recognition, but also in a wide range of applications such as motion analysis, tracking, 3D scene understanding etc. In the context of activity recognition, local features are increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational requirements, their performance is still limited for real world applications due to a lack of contextual information and models not being tailored to specific activities. We propose a new activity representation framework to address the shortcomings of the popular, but simple bag-of-words approach. In our framework, first multiple instance SVM (mi-SVM) is used to identify positive features for each action category and the k-means algorithm is used to generate a codebook. Then locality-constrained linear coding is used to encode the features into the generated codebook, followed by spatio-temporal pyramid pooling to convey the spatio-temporal statistics. Finally, an SVM is used to classify the videos. Experiments carried out on two popular datasets with varying complexity demonstrate significant performance improvement over the base-line bag-of-feature method.

The use of high dynamic range luminance mapping in the assessment, understanding and defining of visual issues in post occupancy building assessment

The international focus on embracing daylighting for energy efficient lighting purposes and the corporate sector’s indulgence in the perception of workplace and work practice “transparency” has spurned an increase in highly glazed commercial buildings. This in turn has renewed issues of visual comfort and daylight-derived glare for occupants. In order to ascertain evidence, or predict risk, of these events; appraisals of these complex visual environments require detailed information on the luminances present in an occupant’s field of view. Conventional luminance meters are an expensive and time consuming method of achieving these results. To create a luminance map of an occupant’s visual field using such a meter requires too many individual measurements to be a practical measurement technique. The application of digital cameras as luminance measurement devices has solved this problem. With high dynamic range imaging, a single digital image can be created to provide luminances on a pixel-by-pixel level within the broad field of view afforded by a fish-eye lens: virtually replicating an occupant’s visual field and providing rapid yet detailed luminance information for the entire scene. With proper calibration, relatively inexpensive digital cameras can be successfully applied to the task of luminance measurements, placing them in the realm of tools that any lighting professional should own. This paper discusses how a digital camera can become a luminance measurement device and then presents an analysis of results obtained from post occupancy measurements from building assessments conducted by the Mobile Architecture Built Environment Laboratory (MABEL) project. This discussion leads to the important realisation that the placement of such tools in the hands of lighting professionals internationally will provide new opportunities for the lighting community in terms of research on critical issues in lighting such as daylight glare and visual quality and comfort.

The role of microcomputer-based laboratory display in supporting the construction of new understanding in kinematics

Teachers' failure to utilise MBL activities more widely may be due to not recognising their capacity to transform the nature of laboratory activities to be more consistent with contemporary constructivist theories of learning. This research aimed to increase understanding of how MBL activities specifically designed to be consistent with a constructivist theory of learning support or constrain student construction of understanding. The first author conducted the research with his Year 11 physics class of 29 students. Dyads completed nine tasks relating to kinematics using a Predict-Observe-Explain format. Data sources included video and audio recordings of students and teacher during four 70-minute sessions, students' display graphs and written notes, semi-structured student interviews, and the teacher's journal. The study identifies the actors and describes the patterns of interactions in the MBL. Analysis of students' discourse and actions identified many instances where students' initial understanding of kinematics were mediated in multiple ways. Students invented numerous techniques for manipulating data in the service of their emerging understanding. The findings are presented as eight assertions. Recommendations are made for developing pedagogical strategies incorporating MBL activities which will likely catalyse student construction of understanding.