Object Pattern Research Articles

Research on Object Tracking Based on Graph Model in Sports Video

This article is about object tracking based on graph modeling. Object tracking is usually initialized by object detection methods. The fundamental hypothesis is that the object's pattern can be separated from its surrounding background sufficiently. However, for some objects, e.g., the ball in broadcast soccer videos, it is hard to extract effective features to detect the ball in a single video frame. The strategy adopted here is to identify the object's candidate regions in several consecutive frames, and then use a graph to construct the relationship between candidate regions. Finally, a Viterbi algorithm is used to extract the optimal path of the graph as the object's trajectory. This process is called short-term tracking. Then, it is used to initialize a Kalman filter to perform long-term tracking. In the process of tracking, the tracked region is verified to determine whether tracking is a failure, and short-term tracking is restarted if a failure happens.

Feedback Convolutional Neural Network for Visual Localization and Segmentation.

Feedback is a fundamental mechanism existing in the human visual system, but has not been explored deeply in designing computer vision algorithms. In this paper, we claim that feedback plays a critical role in understanding convolutional neural networks (CNNs), e.g., how a neuron in CNNs describes an object's pattern, and how a collection of neurons form comprehensive perception to an object. To model the feedback in CNNs, we propose a novel model named Feedback CNN and develop two new processing algorithms, i.e., neural pathway pruning and pattern recovering. We mathematically prove that the proposed method can reach local optimum. Note that Feedback CNN belongs to weakly supervised methods and can be trained only using category-level labels. But it possesses a powerful capability to accurately localize and segment category-specific objects. We conduct extensive visualization analysis, and the results reveal the close relationship between neurons and object parts in Feedback CNN. Finally, we evaluate the proposed Feedback CNN over the tasks of weakly supervised object localization and segmentation, and the experimental results on ImageNet and Pascal VOC show that our method remarkably outperforms the state-of-the-art ones.

A Neural Model of MST and MT Explains Perceived Object Motion during Self-Motion.

When a moving object cuts in front of a moving observer at a 90° angle, the observer correctly perceives that the object is traveling along a perpendicular path just as if viewing the moving object from a stationary vantage point. Although the observer's own (self-)motion affects the object's pattern of motion on the retina, the visual system is able to factor out the influence of self-motion and recover the world-relative motion of the object (Matsumiya and Ando, 2009). This is achieved by using information in global optic flow (Rushton and Warren, 2005; Warren and Rushton, 2009; Fajen and Matthis, 2013) and other sensory arrays (Dupin and Wexler, 2013; Fajen et al., 2013; Dokka et al., 2015) to estimate and deduct the component of the object's local retinal motion that is due to self-motion. However, this account (known as "flow parsing") is qualitative and does not shed light on mechanisms in the visual system that recover object motion during self-motion. We present a simple computational account that makes explicit possible mechanisms in visual cortex by which self-motion signals in the medial superior temporal area interact with object motion signals in the middle temporal area to transform object motion into a world-relative reference frame. The model (1) relies on two mechanisms (MST-MT feedback and disinhibition of opponent motion signals in MT) to explain existing data, (2) clarifies how pathways for self-motion and object-motion perception interact, and (3) unifies the existing flow parsing hypothesis with established neurophysiological mechanisms. To intercept targets, we must perceive the motion of objects that move independently from us as we move through the environment. Although our self-motion substantially alters the motion of objects on the retina, compelling evidence indicates that the visual system at least partially compensates for self-motion such that object motion relative to the stationary environment can be more accurately perceived. We have developed a model that sheds light on plausible mechanisms within the visual system that transform retinal motion into a world-relative reference frame. Our model reveals how local motion signals (generated through interactions within the middle temporal area) and global motion signals (feedback from the dorsal medial superior temporal area) contribute and offers a new hypothesis about the connection between pathways for heading and object motion perception.

Mapping microscope object polarized emission to the back focal plane pattern.

The back focal plane (BFP) intensity pattern from a high-aperture objective separately maps far- and near-field emission from dipoles near a bare glass or metal-film-coated glass/aqueous interface. Total internal reflection (TIR) excitation of a fluorescent sample gave a BFP pattern interpreted in terms of fluorescent dipole orientation and distance from the interface. Theoretical consideration of this system led to identification of emission characteristics that remove a dipole orientation degeneracy in conventional microscope fluorescence polarization measurements. BFP pattern inspection removes the degeneracy. Alternatively, a BFP mask blocking a small fraction of emitted light in a standard imaging microscope prevents uniform collection of the BFP intensity and also eliminates the degeneracy. The BFP pattern from a single photoactivated photoactivatable green fluorescent protein (PAGFP) tagged myosin in a muscle fiber was observed despite the large background light from the highly concentrated myosin tagged with unphotoactivated PAGFP. This was accomplished by imaging the pattern from a nontelecentric plane, where most of the background intensity's pattern was translated laterally from the single-molecule object's pattern. TIR/BFP pattern imaging requires a simple alteration of the fluorescence microscope and is consistent with single-molecule imaging in a fluorophore dense three-dimensional object like a muscle fiber.

A Novel Spatial Filter System Compensates the Measurement Error Caused by Object's Pattern.

Spatial Filters detect the components of a specific spatial frequency contained in optical pattern on object's surface, and the movement or velocity of it are estimated by measuring the frequency of the filter's output. However, the error of the conventional method increase in cases of low speed measurement, small amount of composition of a spatial filter frequency, or large change of patterns.We developed a novel spatial filter in which a CCD line sensor was used to detect object's pattern and DSP (TMS 32025) performed calculation of spatial filters. We also analyzed about the phenomena that measurement error increase in several conditions of the patterns on object's surface, and developed a method which compensates this error. This paper presents the system configuration, the analysis of measurement error, the compensation method, and experimental results show that this method drastically reduce the measurement error caused by object's pattern.