In many robotics and automation applications, it is often required to detect a given object and determine its pose (position and orientation) from input images with high speed, high robustness to photometric changes, and high pose accuracy. We propose a new object matching method that improves efficiency over existing approaches by decomposing orientation and position estimation into two cascade steps. In the first step, an initial position and orientation is found by matching with Histogram of Oriented Gradients (HOG), reducing orientation search from 2D template matching to 1D correlation matching. In the second step, a more precise orientation and position is computed by matching based on Dominant Orientation Template (DOT), using robust edge orientation features. The cascade combination of the HOG and DOT feature for high-speed and robust object matching is the key novelty of the proposed method. Experimental evaluation was performed with real-world single-object and multi-object inspection datasets, using software implementations on an Atom CPU platform. Our results show that the proposed method achieves significant speed improvement compared to an already accelerated template matching method at comparable accuracy performance.
We propose a method for defect detection based on taking the sign information of Walsh Hadamard Transform (WHT) coefficients. The core of the proposed algorithm involves only three steps that can all be implemented very efficiently: applying the forward WHT, taking the sign of the transform coefficients, and taking an inverse WHT using only the sign information. Our implementation takes only 7 milliseconds for a 512 × 512 image on a PC platform. As a result, the proposed method is more efficient than the PHase Only Transform (PHOT) method and other methods in literature. In addition, the proposed approach is capable of detecting defects of varying shapes, by combining the 2-dimensional WHT and 1-dimensional WHT; and can detect defects in images with strong object boundaries by utilizing a reference image. The proposed algorithm is robust over different background image patterns and varying illumination conditions. We evaluated the proposed method both visually and quantitatively and obtained good results on images from various defect detection applications.
We proposed a novel approach to automatic classification of Diabetic Retinopathy (DR) images and retrieval of
clinically-relevant DR images from a database. Given a query image, our approach first classifies the image into one of
the three categories: microaneurysm (MA), neovascularization (NV) and normal, and then it retrieves DR images that
are clinically-relevant to the query image from an archival image database. In the classification stage, the query DR
images are classified by the Multi-class Multiple-Instance Learning (McMIL) approach, where images are viewed as
bags, each of which contains a number of instances corresponding to non-overlapping blocks, and each block is
characterized by low-level features including color, texture, histogram of edge directions, and shape. McMIL first learns
a collection of instance prototypes for each class that maximizes the Diverse Density function using Expectation-
Maximization algorithm. A nonlinear mapping is then defined using the instance prototypes and maps every bag to a
point in a <i>new multi-class bag feature space</i>. Finally a multi-class Support Vector Machine is trained in the multi-class
bag feature space. In the retrieval stage, we retrieve images from the archival database who bear the same label with the
query image, and who are the top K nearest neighbors of the query image in terms of similarity in the multi-class bag
feature space. The classification approach achieves high classification accuracy, and the retrieval of clinically-relevant
images not only facilitates utilization of the vast amount of hidden diagnostic knowledge in the database, but also
improves the efficiency and accuracy of DR lesion diagnosis and assessment.
In the visual tracking domain, Particle Filtering (PF) can become quite inefficient when being applied into high dimensional state space. Rao-Blackwellisation <sup></sup> has been shown to be an effective method to reduce the size of the state space by marginalizing out some of the variables analytically <sup></sup>. In this paper based on our previous work <sup></sup> we proposed RBPF tracking algorithm with adaptive system noise model. Experiments using both simulation data and real data show that the proposed RBPF algorithm with adaptive noise variance improves its performance significantly over conventional Particle Filter tracking algorithm. The improvements manifest in three aspects: increased estimation accuracy, reduced variance for estimates and reduced particle numbers are needed to achieve the same level of accuracy.