Local Intensity Differences Research Articles

Fast and robust infrared small target detection based on a combination of hand-designed features and machine-designed features

ABSTRACT Infrared small target detection is widely used in precision guided weapons and early warning systems. It is very difficult to detect small target in infrared image because the target is small in size and weak in texture information. The traditional methods can’t make full use of the characteristics of the target which results in a low detection rate and a high false alarm rate, and do not consider the complexity of the algorithm which makes it difficult to apply to systems with high real-time requirements. This letter proposes a method that combines hand-designed features and machine-designed features for fast and accurate infrared small target detection. First of all, the region of interest is extracted by the proposed local weighted intensity difference method and local eight-direction gradient method. Then, the detection decision map is constructed to improve the detection speed and compose the decomposed target. Finally, the non-translation invariant CoordConv is used to detect target in the region of interest, which solves the defect that the translation invariance of traditional convolution loses the hand-designed features in the region of interest. Numerous experimental results demonstrate our method has the best detection performance compared with baseline methods, while keeps the lowest detection time.

Infrared maritime dim small target detection based on spatiotemporal cues and directional morphological filtering

The existing small target detection algorithms will suffer severe performance deterioration when the weak target is submerged in heavy cluttered infrared (IR) maritime image. To settle this problem, a small target detection scheme is developed based on spatiotemporal cues and multidirectional morphological filtering. Initially, considering the small target will be isotropic because of the point spread function of the long-distance thermal imaging, while background edge clutters are generally local directional, the multidirectional structuring elements (MSEs) are constructed. By incorporating constructed MSEs and morphological operations, the directional morphological filtering (DMF) is established to measure the multidirectional differences between target region and local surroundings. Then, according to the brightness and isotropic Gaussian-like shape of small target in local spatial domain, the local intensity difference measure (LIDM) and the local Gaussian-like shape measure (LGSM) are presented to differentiate the small target from background clutters. After that, in order to integrate the two spatial properties, the multidirectional improved top-hat filter (MITHF) is proposed by fusing LIDM and LGSM to highlight potential small targets and suppress strong structural edge clutters. Finally, considering the consistency of targets and the fluctuation of sea clutters in temporal domain, a new appearance descriptor namely histogram of oriented morphological filtering (HOMF) is designed to characterize the small target by fully exploiting the advantages of DMF, and the HOMF-based multi-frame confirmation strategy (HMCS) is developed to further identify real small targets and eliminate false alarms. Extensive experiments prove that proposed algorithm is superior to the compared methods, especially for dim small target buried in intricate maritime background clutter.

Infrared Small Maritime Target Detection Based on Integrated Target Saliency Measure

Robust and effective detection of a small target in an infrared maritime image is a key technology of maritime target search and tracking applications. Infrared small target detection is a challenging task due to the factors such as dim small targets and various complex backgrounds caused by sun glitters and strong waves. In this article, the integrated target saliency measure (ITSM) based on local and nonlocal spatial information is proposed to improve target detection performance. We combine local heterogeneity property of targets and nonlocal self-correlation property of background with targets' sparsity to separate real targets from background clutters. First, local heterogeneity calculation based on cross-window standard deviation (CSD) is proposed to extract candidate targets preliminarily, which enhances the local intensity difference between small targets and neighboring background. Meanwhile, low-rank representation (LRR) is applied to background prediction and removal, which is followed by adaptive threshold segmentation to enhance target saliency. Finally, we integrate the results obtained from the two steps mentioned above to further enhance targets and suppress background clutters. Then, real targets are extracted by an iterative threshold on the integrated map so as to generate the seed map, in addition, the target expansion strategy is exploited to keep full target areas. Experimental results on six datasets show that the proposed method outperforms the state-of-the-art methods in terms of robustness and target detection accuracy.

Magnetic Resonance Image Quality Assessment by Using Non-Maximum Suppression and Entropy Analysis.

An investigation of diseases using magnetic resonance (MR) imaging requires automatic image quality assessment methods able to exclude low-quality scans. Such methods can be also employed for an optimization of parameters of imaging systems or evaluation of image processing algorithms. Therefore, in this paper, a novel blind image quality assessment (BIQA) method for the evaluation of MR images is introduced. It is observed that the result of filtering using non-maximum suppression (NMS) strongly depends on the perceptual quality of an input image. Hence, in the method, the image is first processed by the NMS with various levels of acceptable local intensity difference. Then, the quality is efficiently expressed by the entropy of a sequence of extrema numbers obtained with the thresholded NMS. The proposed BIQA approach is compared with ten state-of-the-art techniques on a dataset containing MR images and subjective scores provided by 31 experienced radiologists. The Pearson, Spearman, Kendall correlation coefficients and root mean square error for the method assessing images in the dataset were 0.6741, 0.3540, 0.2428, and 0.5375, respectively. The extensive experimental evaluation of the BIQA methods reveals that the introduced measure outperforms related techniques by a large margin as it correlates better with human scores.

Robust Texture Description Using Local Grouped Order Pattern and Non-Local Binary Pattern

Local binary pattern (LBP) and its many variants have shown effectiveness for texture classification. However, most of these LBP methods focus on encoding local intensity differences between a central pixel and its neighboring sampling points and consequently have two major problems: 1) they are unable to describe the intensity order relationships among neighboring sampling points, and 2) they fail to capture long-range pixel interactions that take place outside a compact neighborhood. In view of these problems, in this paper we propose two novel operators, called local grouped order pattern (LGOP) and non-local binary pattern (NLBP), for texture description. For the first problem, LGOP groups the neighboring sampling points by referring to a dominant direction and encodes the groupwise intensity order relationships. For the second problem, NLBP computes several anchors based on global image statistics and progressively encodes non-local intensity differences between the neighboring sampling points and anchors. Finally, we combine LGOP and NLBP via central pixel encoding to construct discriminative histogram features as texture descriptor LGONBP. Experiments on four texture benchmark databases (i.e., Outex, CUReT, UMD and KTH-TIPS) demonstrate the superiority of LGONBP over state-of-the-art LBP variants for texture classification under both noise-free and noisy conditions. The code is available at <uri>https://github.com/stc-cqupt/LGONBP</uri>.

Active Contours Driven by Local and Global Region-Based Information for Image Segmentation

Intensity inhomogeneity and noise are two major parts in image segmentation. Aiming at these problems, this work proposes a novel hybrid active contour method which combines local and global statistical information into an improved signed pressure force (SPF) function. First, by considering the global information extracted from a region of interest, a new global-based SPF function is created that effectively adjusts the signs of the pressure force inside and outside the evolving curve. Second, a new local-based SPF function utilizes the normalized local intensity differences as the coefficients of local internal and external regions, which can segment complicated areas easily. Third, by combing the global-based SPF and the local-based SPF functions, an improved hybrid SPF function is constructed based on active contour approach. Experiments on many kinds of real and synthetic images show that our method makes superior segmentation accuracy and is more robust to initial contour and noises.

Infrared Moving Small-Target Detection Using Spatial–Temporal Local Difference Measure

Effectiveness and false alarm (FA) suppression are key issues in infrared (IR) moving small-target detection. In this letter, we propose a novel spatial–temporal local difference measure (STLDM) algorithm to detect a moving IR small target. The method we propose involves three steps. First, we block off three frames in a certain range of time (temporal) domain. Next, in a 3-D spatial–temporal domain, we analyze the local grayscale intensity difference of the small targets moving between the three frames and calculate the difference between the grayscale intensity in the center area and the grayscale intensity in the eight directions in the area surrounding the target. Finally, we segment the small target in a detection result map. The results of our experiment demonstrate that our proposed STLDM method has a higher rate of detection of IR moving small targets, as well as fewer FAs than other existing methods.

Active Contour Driven by Weighted Hybrid Signed Pressure Force for Image Segmentation

This study presents a novel active contour model (ACM) driven by weighted global and local region-based signed pressure force (SPF) to segment images in the presence of intensity inhomogeneity and noise. First, an adaptive weighted global region-based SPF (GRSPF) function as the driving centers is designed based on the global image information, which is based on the normalized global intensity to update the weights of the inner and outer regions of the curve during iterations. Second, by introducing the normalized absolute local intensity differences as the weighs of the inner and outer regions, an adaptive weighted local region-based SPF (LRSPF) function is similarly defined. Third, instead of setting a fixed force, a force propagation function is introduced to automatically balance the interior and exterior forces according to the image feature. Meanwhile, by combing the adaptive GWSPF and LWSPF functions, a weighted hybrid region-based SPF function is defined, which can improve the efficiency and accuracy of the proposed model. The experimental results on real images demonstrate that the proposed model is more robust than the popular region-based ACMs for segmenting images with intensity inhomogeneity and noise. The code is available at https://github.com/fangchj2002/WHRSPF .

Local Neighborhood Intensity Pattern–A new texture feature descriptor for image retrieval

In this paper, a new texture descriptor based on the local neighborhood intensity difference is proposed for content based image retrieval (CBIR). For computation of texture features like Local Binary Pattern (LBP), the center pixel in a 3 × 3 window of an image is compared with all the remaining neighbors, one pixel at a time to generate a binary bit pattern. It ignores the effect of the adjacent neighbors of a particular pixel for its binary encoding and also for texture description. The proposed method is based on the concept that neighbors of a particular pixel hold significant amount of texture information that can be considered for efficient texture representation for CBIR. The main impact of utilizing the mutual relationship among adjacent neighbors is that we do not rely on the sign of the intensity difference between central pixel and one of its neighbors (Ii) only, rather we take into account the sign of difference values between Ii and its adjacent neighbors along with the central pixels and same set of neighbors of Ii. This makes our pattern more resistant to illumination changes. Moreover, most of the local patterns including LBP concentrates mainly on the sign information and thus ignores the magnitude. The magnitude information which plays an auxiliary role to supply complementary information of texture descriptor, is integrated in our approach by considering the mean of absolute deviation about each pixel Ii from its adjacent neighbors. Taking this into account, we develop a new texture descriptor, named as Local Neighborhood Intensity Pattern (LNIP) which considers the relative intensity difference between a particular pixel and the center pixel by considering its adjacent neighbors and generate a sign and a magnitude pattern. Finally, the sign pattern (LNIPS) and the magnitude pattern (LNIPM) are concatenated into a single feature descriptor to generate a more effective feature descriptor. The proposed descriptor has been tested for image retrieval on four databases, including three texture image databases - Brodatz texture image database, MIT VisTex database and Salzburg texture database and one face database - AT&T face database. The precision and recall values observed on these databases are compared with some state-of-art local patterns. The proposed method showed a significant improvement over many other existing methods.

Local neighborhood difference pattern: A new feature descriptor for natural and texture image retrieval

A new image retrieval technique using local neighborhood difference pattern (LNDP) has been proposed for local features. The conventional local binary pattern (LBP) transforms every pixel of image into a binary pattern based on their relationship with neighboring pixels. The proposed feature descriptor differs from local binary pattern as it transforms the mutual relationship of all neighboring pixels in a binary pattern. Both LBP and LNDP are complementary to each other as they extract different information using local pixel intensity. In the proposed work, both LBP and LNDP features are combined to extract the most of the information that can be captured using local intensity differences. To prove the excellence of the proposed method, experiments have been conducted on four different databases of texture images and natural images. The performance has been observed using well-known evaluation measures, precision and recall and compared with some state-of-art local patterns. Comparison shows a significant improvement in the proposed method over existing methods.

Saliency-based Pedestrian Detection in Far Infrared Images

Night time pedestrian detection is more and more important in advanced driver assistant systems (ADAS). Traditional pedestrian detection algorithms in far infrared (FIR) images lack accuracy and have long processing times. Focusing on this issue, in this paper, a visual saliency-based pedestrian detection algorithm is proposed. First, areas that contain suspected pedestrians are detected using a fusion saliency-based method. Then, the sub-image of the suspected pedestrian is used as an input to a histogram of local intensity difference feature and cross kernel-based support vector machine classifier to make a final determination. Experiments performed using a real FIR road image data set demonstrated that the proposed fusion saliency-based region of interest (ROI) detection method has the largest pedestrian inclusion rate and the smallest ROI proportion compared with three other methods. Besides, compared with existing state-of-the-art pedestrian detection algorithms, the proposed method demonstrates a much higher pedestrian detection rate with a comparably short processing time.

Robust noise region-based active contour model via local similarity factor for image segmentation

Image segmentation using a region-based active contour model could present difficulties when its noise distribution is unknown. To overcome this problem, this paper proposes a novel region-based model for the segmentation of objects or structures in images by introducing a local similarity factor, which relies on the local spatial distance within a local window and local intensity difference to improve the segmentation results. By using this local similarity factor, the proposed method can accurately extract the object boundary while guaranteeing certain noise robustness. Furthermore, the proposed algorithm completely avoids the pre-processing steps typical of region-based contour model segmentation, resulting in a higher preservation of image details. Experiments performed on synthetic images and real word images demonstrate that the proposed algorithm, as compared with the state-of-art algorithms, is more efficient and robust to higher noise level manifestations in the images.

MO-DE-207A-03: Characterization of Potential Gains in a Novel Exponential 4DCT Reconstruction Algorithm

Purpose: To sample the breathing cycle and obtain accurate target volumes, 4DCT requires the entire field of view (FOV) to be illuminated during one breathing period. However, interplay effects between internal motion and couch pitch may adversely impact the temporal resolution, thereby blurring object edges. This work performs a characterization of exponential 4DCT reconstruction to highlight potential gains over standard cos2 weighted reconstruction algorithm. Methods: A respiratory motion platform translated several objects in the superior-inferior direction at varied breathing rates (8–20 breaths/minute) and couch pitches (0.06–0.1 A.U.) to evaluate the interplay between parameters. Ten-phase 4DCTs were acquired (0.5s rotation) and data were reconstructed with cos2 and exponential weighting factors. To isolate a metric to quantify temporal resolution (i.e. remove couch interplay effects), a small object was translated in the anterior-posterior direction. Full-width half maximum (FWHM) intensity distributions were quantified between reconstruction algorithms and a static case. 4DCT sinogram data for fifteen lung and abdomen patients were retrospectively reconstructed using cos2 and exponential weighting factors. Image subtractions were generated to elucidate intensity and boundary differences. Results: After taking the static object size into account, the FWHM of exponential weighting was 1.5±1.2 mm (range: 0.1–4.1) as compared to the FWHM of cos2 3.4±2.4 mm (range: 0.3–8.0). This translated to estimated improvements in temporal resolution of 33.5±48.2 ms (range: 0.03–170.9). Slower breathing periods, faster couch pitches, and intermediate 4DCT phases where velocity is highest showed a tendency to have the largest improvements in temporal resolution with exponential reconstruction. For patient cases, coronal views showed less blurring at object boundaries and local intensity differences near moving features. Conclusion: Exponential weighted 4DCT offers potential for improving temporal resolution in 4DCT, thus improving the image sharpness near the boundaries. Understanding the potential implications on delineation ability is an important next step of this work. The submitting institution holds research agreements with Philips Healthcare.

MO‐FG‐204‐05: Evaluation of a Novel Algorithm for Improved 4DCT Resolution

Purpose:Accurate tumor motion characterization is critical for increasing the therapeutic ratio of radiation therapy. To accommodate the divergent fan‐beam geometry of the scanner, the current 4D‐CT algorithm utilizes a larger temporal window to ensure that pixel values are valid throughout the entire FOV. To minimize the impact on temporal resolution, a cos2 weighting is employed. We propose a novel exponential weighting (“exponential”) 4DCT reconstruction algorithm that has a sharper slope and provides a more optimal temporal resolution.Methods:A respiratory motion platform translated a lung‐mimicking Styrofoam slab with several high and low‐contrast inserts 2 cm in the superior‐inferior direction. Breathing rates (10–15 bpm) and couch pitch (0.06–0.1 A.U.) were varied to assess interplay between parameters. Multi‐slice helical 4DCTs were acquired with 0.5 sec gantry rotation and data were reconstructed with cos2 and exponential weighting. Mean and standard deviation were calculated via region of interest analysis. Intensity profiles evaluated object boundaries. Retrospective raw data reconstructions were performed for both 4DCT algorithms for 3 liver and lung cancer patients. Image quality (temporal blurring/sharpness) and subtraction images were compared between reconstructions.Results:In the phantom, profile analysis revealed that sharper boundaries were obtained with exponential reconstructions at transitioning breathing phases (i.e. mid‐inhale or mid‐exhale). Reductions in full‐width half maximum were ∼1 mm in the superior‐inferior direction and appreciable sharpness could be observed in difference maps. This reduction also yielded a slight reduction in target volume between reconstruction algorithms. For patient cases, coronal views showed less blurring at object boundaries and local intensity differences near the tumor and diaphragm with exponential weighted reconstruction.Conclusion:Exponential weighted 4DCT offers potential for improving image sharpness in 4DCT. Comparisons with true object extent using static CTs of varied phantom positions are necessary to confirm these findings. Future work with additional patient cases is warranted.Research partially sponsored by Philips Healthcare

Fusion Based Seamless Mosaic for Remote Sensing Images

A fusion based seamless mosaic method for stitching remote sensing images is introduced in this paper. The proposed method focuses on one major problem in the process of mosaic: how to generate visually pleasant stitching result in the cases of misalignment, global and local intensity differences between images. First, two partially overlapped images are decomposed into high-frequency components and low-frequency components with Gaussian low-pass filter. Second, by considering the information characteristics contained in both separated components, different mosaic schemes are designed to accomplish stitching process accordingly. For the low-frequency components consisting of coarse shape and illumination information, two-dimension weighted blending rule is utilized to achieve smoothing transition. For the high-frequency components including rich details, an improved seam searching strategy based on dynamic programming is introduced. With the obtained stitching seam guiding the stitching process, visible structural break can be avoided. Finally, the mosaic result is produced by linearly composing both stitching results of different components together. Experimental results demonstrate the effectiveness of the proposed method in generating seamless mosaic results without introducing any unexpected blurring or artifacts.

An improved local binary pattern for texture classification

This paper proposes an improved robust descriptor: the Joint Local Binary Patterns with Weber-like responses (JLBPW). The JLBPW descriptor mainly solves two problems of the existing Local Binary Pattern (LBP) method. The existing LBP methods discard the local intensity differences by holding their binary information. And the correlation of patterns under different scales is also ignored when the multi-resolution technique is used by the LBP methods. Aiming at the two problems, the JLBPW descriptor organizes the ignored local intensity differences according to the Weber's law that is discovered from psychological experiments. And the organized differences are set as responses of the corresponding joint patterns. The proposed descriptor supplies more information to describe local structures of images. Experiments on two representative databases demonstrate that the proposed descriptor is superior to other modern approaches.

Histograms of local intensity differences for pedestrian classification in far‐infrared images

Presented is an intensity-based feature extraction method for pedestrian classification in far-infrared (FIR) images. The underlying idea of the method is that only intensity differences between neighbouring pixels can represent both the direction and the magnitude of the gradient, as FIR images are characterised by monotonic grey-level changes. A new intensity-based feature called the histogram of local intensity differences (HLID) is introduced which is a modified version of the well-known histograms of oriented gradients (HOGs) feature. Experiments show that the HLID is more suited to FIR images than HOGs in terms of both accuracy and computational efficiency.

Accumulation of local maximum intensity for feature enhanced volume rendering

Maximum Intensity Difference Accumulation (MIDA) combines the advantage of Direct Volume Rendering (DVR) and Maximum Intensity Projection (MIP). However, many features with local maximum intensity are still missing in the final rendering image. This paper presents a novel approach to focus on features with local maximum intensity within the dataset. Moving Least Squares (MLS) is used to smooth each ray profile during the raycasting in order to eliminate noise in the data and to highlight significant transition points on the profile. We then adopt a local minimum-point searching method to analyze the ray profile, and identify the transition points that mark the local maximum intensity points within the dataset. At the rendering stage, we implement a novel local intensity difference accumulation (LIDA) to accumulate the colors and opacity. Surface shading is introduced to improve the spatial cues of the features. We also employ tone-reduction to preserve the original local contrast. Our approach can highlight local features in the dataset without involving the adjustment of transfer functions. The experiments demonstrate high-quality rendering results at an interactive frame rate.

Local intensity distribution descriptor for object detection

A novel local intensity distribution (LID) descriptor for object detection is proposed. By capturing the distribution of local intensity differences effectively, the LID descriptor is insensitive to illumination changes while being more compact and discriminative compared with the popular local binary pattern. Two LID descriptors can be efficiently compared using the Kullback-Leibler distance. The efficacy and efficiency of the proposed descriptor have been verified in the task of detecting humans from static images.

On the response of the European climate to solar/geomagnetic long-term activity

The response of the European climate to long-term solar/geomagnetic activity is investigated using surface-air temperature and solar/geomagnetic indices. A set of 21 time series of air temperatures measured at European stations between 1900 and 2006, and 4 European and 14 Romanian stations with 150-year-long records, were used. Strong and coherent solar signals were found at Schwabe and Hale solar-cycle timescales, with peak-to-trough amplitudes of several degrees, and 0.6 ˚C to 0.8 ˚C, respectively. Interdecadal and centennial trends as defined by 11-year and 22-year running averages, respectively, of the annual mean time series differ significantly from corresponding trends in solar/geomagnetic activity, which indicates the presence of temperature variations at a 40-year timescale that are possibly related to the internal dynamics of the atmospheric system. The data show similar temporal behaviors at all of the stations analyzed, with amplitude differences that can be understood in terms of large-scale atmospheric circulation patterns that are influenced by the solar/geomagnetic forcing at the corresponding timescales, although with local intensity differences.