Active Basis Model Research Articles

Transmission line detection based on a hierarchical and contextual model for aerial images

Due to highly cluttered backgrounds and limited visual features, transmission line detection (TLD) in complex and natural outdoor environments is a difficult task. Motivated by image parsing, a TLD algorithm that utilizes a decomposition structure and contextual information is proposed. Considering that cables are generally associated with the presence of pylons, correlations between pylons and cables, as well as correlations among different cable segments, are defined as the contextual information, which is described using a hierarchical model with the structure of an and-or graph. First, pylons in images are detected via an active basis model, which is an appearance model that uses sparse representation. Next, according to the number of pylons, the bottom-up inference in the hierarchical model selects different procedures and corresponding operations to detect cables. Multiple experiments are performed on aerial images captured in practical powerline inspection tasks. The experimental results illustrate that our TLD algorithm can effectively manage images captured under various landforms at different visual distances and from different viewpoints. For highly cluttered environments in particular, our algorithm has obvious advantages in terms of detection performance compared with existing approaches.

A dual fast and slow feature interaction in biologically inspired visual recognition of human action

Computational neuroscience studies have examined the human visual system through functional magnetic resonance imaging (fMRI) and identified a model where the mammalian brain pursues two independent pathways for recognizing biological movement tasks. On the one hand, the dorsal stream analyzes the motion information by applying optical flow, which considers the fast features. On the other hand, the ventral stream analyzes the form information with slow features. The proposed approach suggests that the motion perception of the human visual system comprises fast and slow feature interactions to identify biological movements. The form features in the visual system follow the application of the active basis model (ABM) with incremental slow feature analysis (IncSFA). Episodic observation is required to extract the slowest features, whereas the fast features update the processing of motion information in every frame. Applying IncSFA provides an opportunity to abstract human actions and use action prototypes. However, the fast features are obtained from the optical flow division, which gives an opportunity to interact with the system as the final recognition is performed through a combination of the optical flow and ABM-IncSFA information and through the application of kernel extreme learning machine. Applying IncSFA into the ventral stream and involving slow and fast features in the recognition mechanism are the major contributions of this research. The two human action datasets for benchmarking (KTH and Weizmann) and the results highlight the promising performance of this approach in model modification.

Vehicle detection, counting and classification in various conditions

Intelligent transportation systems have received a lot of attention in the last decades. Vehicle detection is the key task in this area and vehicle counting and classification are two important applications. In this study, the authors proposed a vehicle detection method which selects vehicles using an active basis model and verifies them according to their reflection symmetry. Then, they count and classify them by extracting two features: vehicle length in the corresponding time-spatial image and the correlation computed from the grey-level co-occurrence matrix of the vehicle image within its bounding box. A random forest is trained to classify vehicles into three categories: small (e.g. car), medium (e.g. van) and large (e.g. bus and truck). The proposed method is evaluated using a dataset including seven video streams which contain common highway challenges such as different lighting conditions, various weather conditions, camera vibration and image blurring. Experimental results show the good performance of the proposed method and its efficiency for use in traffic monitoring systems during the day (in the presence of shadows), night and all seasons of the year.

Slow feature action prototypes effect assessment in mechanism for recognition of biological movement ventral stream

In analysis of the brain and visual system functionality, scientific evidence points to two independent processing pathways in recognising biological movement, i.e. dorsal and ventral streams. Motion information generated in the dorsal processing stream is presented as fuzzy optical flow division while ventral processing stream with information of the object form is implemented as an active basis model. The recognition task however still requires decision-making and mutual interaction between these pathways. This process is done using slow features as action prototypes dictionary of biological movements. For motion information interaction, dorsal pathway guides the shared sketch algorithm that leads to decision-making for a more accurate outcome. Extreme learning machine classifier is used for decision-making unit kernel. The proposed approach is tested on the KTH human action database videos. Good performances are indicated compared to existing methods, with good interaction between dorsal and ventral processing streams.

Development of biological movement recognition by interaction between active basis model and fuzzy optical flow division.

Following the study on computational neuroscience through functional magnetic resonance imaging claimed that human action recognition in the brain of mammalian pursues two separated streams, that is, dorsal and ventral streams. It follows up by two pathways in the bioinspired model, which are specialized for motion and form information analysis (Giese and Poggio 2003). Active basis model is used to form information which is different from orientations and scales of Gabor wavelets to form a dictionary regarding object recognition (human). Also biologically movement optic-flow patterns utilized. As motion information guides share sketch algorithm in form pathway for adjustment plus it helps to prevent wrong recognition. A synergetic neural network is utilized to generate prototype templates, representing general characteristic form of every class. Having predefined templates, classifying performs based on multitemplate matching. As every human action has one action prototype, there are some overlapping and consistency among these templates. Using fuzzy optical flow division scoring can prevent motivation for misrecognition. We successfully apply proposed model on the human action video obtained from KTH human action database. Proposed approach follows the interaction between dorsal and ventral processing streams in the original model of the biological movement recognition. The attained results indicate promising outcome and improvement in robustness using proposed approach.

Pedestrian Detection Based on Active Basis

Pedestrian detection from a video sequence is a challenging problem. In this paper, we mainly use active basis model which consists of a small number of Gabor wavelet elements at selected locations and orientations to detect pedestrian. In order to enhance the detection rate, we propose an adaptive background modeling method for background subtraction method to detect objects in video sequence which emphasize background and remove foreground using mask technology. After acquiring many pedestrian templates of different poses and orientations, active basis method can be applied in pose estimation and human action analysis. The detection results indicate that our approach is capable of obtaining better detecting effects and pose estimation even under conditions of noise and illumination changes.

Evaluating a color-based active basis model for object recognition

Wu and coworkers introduced an active basis model (ABM) for object recognition in 2010, in which the learning algorithm tends to sketch edges in textures. A grey-value local power spectrum was used to find a common template and deformable templates from a set of training images and to detect an object in new images by template matching. In this paper, we propose a color-based active basis model (color-based ABM for short), which incorporates color information. We adopt the framework of Wu et al. in the learning, detection, and classification of the color-based ABM. However, in order to improve the performance in object recognition, we modify the framework of Wu et al. by using different color-based features in both the learning and template matching algorithms. In this color-based ABM approach, two types of learning (i.e., supervised learning and unsupervised learning) are also explored. Moreover, the usefulness of the color-based ABM for practical object recognition in computer vision applications is demonstrated and its significant improvement in recognizing objects is reported.

Estimating illumination direction of three-dimensional surface texture based on active basis and Mojette transform

Given an image of a rough surface texture, the approach described here can estimate the direction from which the surface was lit. Unlike previous work, we require neither surface isotropy nor that the texture is included in the training set. The approach is based on active basis and the Mojette transform. The Mojette transform is used to estimate the orientation of the texture; it does so by finding which training samples have similar orientation features. The active basis model is then learned from training images by the shared pursuit algorithm. Next, the base histograms of the test image and textures with similar orientation features in the training set are compared so that the illumination directions can be estimated by minimizing their correlation coefficients.

Learning Active Basis Models by EM-Type Algorithms

EM algorithm is a convenient tool for maximum likelihood model fitting when the data are incomplete or when there are latent variables or hidden states. In this review article we explain that EM algorithm is a natural computational scheme for learning image templates of object categories where the learning is not fully supervised. We represent an image template by an active basis model, which is a linear composition of a selected set of localized, elongated and oriented wavelet elements that are allowed to slightly perturb their locations and orientations to account for the deformations of object shapes. The model can be easily learned when the objects in the training images are of the same pose, and appear at the same location and scale. This is often called supervised learning. In the situation where the objects may appear at different unknown locations, orientations and scales in the training images, we have to incorporate the unknown locations, orientations and scales as latent variables into the image generation process, and learn the template by EM-type algorithms. The E-step imputes the unknown locations, orientations and scales based on the currently learned template. This step can be considered self-supervision, which involves using the current template to recognize the objects in the training images. The M-step then relearns the template based on the imputed locations, orientations and scales, and this is essentially the same as supervised learning. So the EM learning process iterates between recognition and supervised learning. We illustrate this scheme by several experiments.

Learning Active Basis Model for Object Detection and Recognition

This article proposes an active basis model, a shared sketch algorithm, and a computational architecture of sum-max maps for representing, learning, and recognizing deformable templates. In our generative model, a deformable template is in the form of an active basis, which consists of a small number of Gabor wavelet elements at selected locations and orientations. These elements are allowed to slightly perturb their locations and orientations before they are linearly combined to generate the observed image. The active basis model, in particular, the locations and the orientations of the basis elements, can be learned from training images by the shared sketch algorithm. The algorithm selects the elements of the active basis sequentially from a dictionary of Gabor wavelets. When an element is selected at each step, the element is shared by all the training images, and the element is perturbed to encode or sketch a nearby edge segment in each training image. The recognition of the deformable template from an image can be accomplished by a computational architecture that alternates the sum maps and the max maps. The computation of the max maps deforms the active basis to match the image data, and the computation of the sum maps scores the template matching by the log-likelihood of the deformed active basis.