Search

Feature detection is the basis of many computer vision applications. However, the existing feature detectors have poor illumination robustness for various reasons. FAST is a very effective detection method, and is currently widely used for real-time feature detection. The threshold function in the traditional FAST method is a linear function and is unable to deal with the issue of illumination robustness. This paper proposes an illumination-robust feature detection method, the core is an adaptive threshold FAST. The proposed method constructs a threshold function based on neighborhood standard deviation, which successfully solves the problem that the traditional FAST has poor illumination robustness. In addition, a new image preprocessing method consisting of homomorphic filtering and histogram equalization is introduced to the front-end of the proposed method in order to improve the quality of the input image. Compared with state-of-the-art methods, the repeatibility rate of proposed method has been increased several times in the underexposure matching experiment, and the number of repeated features has been increased by dozens of times. Meanwhile, the number of repeated features increased by more than a third on average in the overexposed experiment. The experimental results strongly prove that the proposed method has significant advantages in terms of repeatibility rate, number of repeated features and detection stability evaluation indices. [ABSTRACT FROM AUTHOR]

Saturation and large intensity variations occurred in multi-exposed images offer great challenges to align these images. In this paper, a mutual local-ternary-pattern (MLTP) is proposed to represent differently exposed images for image registration. Different from the classical local ternary pattern (LTP) and its variants, the proposed MLTP has two salient properties: (1) The ternary pattern of one image is not only determined by itself, but also relied on its counterpart; (2) The MLTP is grayscale-adaptive. It is analyzed that the proposed MLTP is a good representation to preserve consistency of differently exposed images. Based on the MLTP-coded images, an efficient linear model derived from Taylor expansion is presented to estimate motion parameters. To improve accuracy and efficiency, image rotation is initially detected by the histogram-based matching, and coarse-to-fine technique is implemented to cope with possibly large movement. Extensive experiments carried out on a variety of synthesized and real multi-exposed images demonstrate that the proposed method is robust to 10 exposure values (EV), which is superior to other methods and current commercial HDR tools. [ABSTRACT FROM AUTHOR]

Feature point detection is the basis of computer vision, and the detection methods with geometric invariance and illumination invariance are the key and difficult problem in the field of feature detection. This paper proposes an illumination-invariant feature point detection method based on neighborhood information. The method can be summarized into two steps. Firstly, the feature points are divided into eight types according to the number of connected neighbors. Secondly, each type of feature points is classified again according to the position distribution of neighboring pixels. The theoretical deduction proves that the proposed method has lower computational complexity than other methods. The experimental results indicate that, when the photometric variation of the two images is very large, the feature-based detection methods are usually inferior, while the learning-based detection methods performs better. However, our method performs better than the learning-based detection method in terms of the number of feature points, the number of matching points, and the repeatability rate stability. The experimental results demonstrate that the proposed method has the best illumination robustness among state-of-the-art feature detection methods. [ABSTRACT FROM AUTHOR]

Geometric model fitting is a fundamental issue in computer vision, and the fitting accuracy is affected by outliers. In order to eliminate the impact of the outliers, the inlier threshold or scale estimator is usually adopted. However, a single inlier threshold cannot satisfy multiple models in the data, and scale estimators with a certain noise distribution model work poorly in geometric model fitting. It can be observed that the residuals of outliers are big for all true models in the data, which makes the consensus of the outliers. Based on this observation, we propose a preference analysis method based on residual histograms to study the outlier consensus for outlier detection in this paper. We have found that the outlier consensus makes the outliers gather away from the inliers on the designed residual histogram preference space, which is quite convenient to separate outliers from inliers through linkage clustering. After the outliers are detected and removed, a linkage clustering with permutation preference is introduced to segment the inliers. In addition, in order to make the linkage clustering process stable and robust, an alternative sampling and clustering framework is proposed in both the outlier detection and inlier segmentation processes. The experimental results also show that the outlier detection scheme based on residual histogram preference can detect most of the outliers in the data sets, and the fitting results are better than most of the state-of-the-art methods in geometric multi-model fitting. [ABSTRACT FROM AUTHOR]