The ability to individuate objects is one of our most fundamental cognitive capacities. Recent research has revealed that, when objects vary in color or luminance alone, infants fail to individuate until 11.5 months. However, color and luminance frequently co-vary in the natural environment, and color and luminance interact in pattern detection, motion detection, and stereopsis. For this reason, we propose that infants may be more likely to individuate when objects vary in both color and luminance. Using the narrow-screen task of Wilcox and Baillargeon, Experiments 1 and 2 assessed 7.5-month-old infants’ ability to individuate uniformly colored objects that either varied in both color and luminance or varied in luminance alone. The results indicated that infants used these features to individuate only when the objects varied in both color and luminance. Thus, when color and luminance co-varied, infants used these features to individuate objects a full 4 months earlier than infants use either feature alone. Experiment 3 further explored the link between color and luminance by assessing 7.5-month-old infants’ ability to use pattern differences to individuate objects. Although infants use pattern differences created from a combination of luminance and color contrast by 7.5 months, results from Experiment 3 indicated that when pattern was created from either color contrast or luminance contrast alone, infants fail to individuate based on pattern. The results of Experiment 3 suggest that it is not the number of feature dimensions that is important, but the unique contribution of both color and luminance that is particularly salient to infants. These studies add to a growing body of literature investigating the interaction of color and luminance in object processing in infants, and have implications for developmental changes in the nature and content of infants’ object representations.

The fundamental goal of this study is to explore why so many students have difficulty learning mathematics. To achieve this goal, this study focuses on why so many students keep making the same errors over a long period of time. To explore such issues, three basic algebra concepts - variable, equation, and function – are used to analyze students’ errors, possible buggy algorithms, and the conceptual basis of these errors: misconceptions. Through the research on these three basic concepts, it is expected that a more general principle of understanding and the corresponding learning difficulties can be illustrated by the case studies. Although students’ errors varied to a great extent, certain types of errors related to students’ misconceptions occurred frequently and repeatedly after one year of additional instruction. Thus, it is possible to identify students’ misconceptions through working on students’ systematic errors. The causes of students’ robust misconceptions were explored by comparing high-achieving and low-achieving students’ understanding of these three concepts at the object (structural) or process (operational) levels. In addition, high achieving students were found to prefer using object (structural) thinking to solve problems even if the problems could be solved through both algebra and arithmetic approaches. It was also found that the relationship between students’ misconception and object-process thinking explained why some misconceptions were particularly difficult to change. Students’ understanding of concepts at either of two stages (process and object) interacted with either of two aspects (correct conception and misconception). When students had understood a concept as a process with misconception, such misconception was particularly hard to change. In addition, other concerns, such as rethinking the misconception of the “equal sign,” the influence of prior experience on students’ learning, misconceptions and recycling curriculum, and developing teachers’ initial subject knowledge were also discussed. The findings of this study demonstrated that the fundamental reason of misconception of “equal sign” was the misunderstanding of either side of equation as a process rather than as an object. Due to the existence of robust misconceptions as stated in this study, the use of recycling curriculum may have negative effect on students’ understanding of mathematics.

An intelligent robot must be able to perceive and reason robustly about its world in terms of objects, among other foundational concepts. The robot can draw on rich data for object perception from continuous sensory input, in contrast to the usual formulation that focuses on objects in isolated still images. Additionally, the robot needs multiple object representations to deal with different tasks and/or different classes of objects. We propose the Object Semantic Hierarchy (OSH), which consists of multiple representations with different ontologies. The OSH factors the problems of object perception so that intermediate states of knowledge about an object have natural representations, with relatively easy transitions from less structured to more structured representations. Each layer in the hierarchy builds an explanation of the sensory input stream, in terms of a stochastic model consisting of a deterministic model and an unexplained "noise" term. Each layer is constructed by identifying new invariants from the previous layer. In the final model, the scene is explained in terms of constant background and object models, and low-dimensional dynamic poses of the observer and objects. The OSH contains two types of layers: the Object Layers and the Model Layers. The Object Layers describe how the static background and each foreground object are individuated, and the Model Layers describe how the model for the static background or each foreground object evolves from less structured to more structured representations. Each object or background model contains the following layers: (1) 2D object in 2D space (2D2D): a set of constant 2D object views, and the time-variant 2D object poses, (2) 2D object in 3D space (2D3D): a collection of constant 2D components, with their individual time-variant 3D poses, and (3) 3D object in 3D space (3D3D): the same collection of constant 2D components but with invariant relations among their 3D poses, and the time-variant 3D pose of the object as a whole. In building 2D2D object models, a fundamental problem is to segment out foreground objects in the pixel-level sensory input from the background environment, where motion information is an important cue to perform the segmentation. Traditional approaches for moving object segmentation usually appeal to motion analysis on pure image information without exploiting the robot's motor signals. We observe, however, that the background motion (from the robot's egocentric view) has stronger correlation to the robot's motor signals than the motion of foreground objects. Based on this observation, we propose a novel approach to segmenting moving objects by learning homography and fundamental matrices from motor signals. In building 2D3D and 3D3D object models, estimating camera motion parameters plays a key role. We propose a novel method for camera motion estimation that takes advantage of both planar features and point features and fuses constraints from both homography and essential matrices in a single probabilistic framework. Using planar features greatly improves estimation accuracy over using point features only, and with the help of point features, the solution ambiguity from a planar feature is resolved. Compared to the two classic approaches that apply the constraint of either homography or essential matrix, the proposed method gives more accurate estimation results and avoids the drawbacks of the two approaches. / text

In this work we address the problem of object recognition and localization from sparse range data. The method is based upon comparing the 7-D error surfaces of objects in various poses, which result from the registration error function between two convolved surfaces. The objects and their pose values are encoded by a small set of feature vectors extracted from the minima of the error surfaces. The problem of object recognition is thus reduced to comparing these feature vectors to find the corresponding error surfaces between the runtime data and a preprocessed database. Specifically, we present a new approach to the problems of pose determination, object recognition and object class recognition. The algorithm has been implemented and tested on both simulated and real data. The experimental results demonstrate the technique to be both effective and efficient, executing at 122 frames per second on standard hardware and with recognition rates exceeding 97% for a database of 60 objects. The performance of the proposed potential well space embedding (PWSE) approach on large size databases was also evaluated on the Princeton Shape Bench- mark containing 1,814 objects. In experiments of object class recognition with the Princeton Shape Benchmark, PWSE is able to provide better classification rates than the previous methods in terms of nearest neighbour classification. In addition, PWSE is shown to (i) operate with very sparse data, e.g., comprising only hundreds of points per image, and (ii) is robust to measurement error and outliers. / Thesis (Ph.D, Electrical & Computer Engineering) -- Queen's University, 2010-01-24 23:07:30.108

Outside of ourselves, exists the object, independent of the human mind. It is the mere presence of the object that enables one to so much as venture to conceive of such abstract realities as Time, Space and other human and inhuman existences. For the object provokes an awakening of consciousness to the being of these three realities: the object renders form and dimension to space, thus providing concrete reference for the human mind. The object transposes time, as it is situated in a precise and historical moment; or, the object may serve as a reflection of another time and space. And ultimately, the object reminds one that the Other exists by bestowing an identity upon it; in fact, the object creates the other's existence. Yet, the object is a being in itself, a reality that remains perpetually indomitable; the object is the Other. / The fictional text, La chasse aux poils, is a compilation of three short stories in which is brought to light the relation existing between the subject and the object.

No description available.

No description available.

No description available.

No description available.

No description available.