We report a generic method for automatic segmentation of endoscopic optical coherence tomography (OCT) images. In this method, OCT images are first processed with - norm minimization based de-noising and smoothing algorithms to increase the signal-to-noise ratio (SNR) and enhance the contrast between adjacent layers. The smoothed images are then formulated into cost graphs based on their vertical gradients. After that, tissue-layer segmentation is performed with the shortest path search algorithm. The efficacy and capability of this method are demonstrated by automatically and robustly identifying all five interested layers of guinea pig esophagus from endoscopic OCT images. Furthermore, thanks to the ultrahigh resolution, high SNR of endoscopic OCT images and the high segmentation accuracy, this method permits optical staining histology and facilitates quantitative analysis of tissue geometric properties, which can be very useful for studying tissue pathologies and potentially aiding clinical diagnosis in real time.

No abstract

No abstract

Naked carp (Gymnocypris przewalskii), endemic to the saline-alkaline Lake Qinghai, have the capacity to tolerate combinations of high salinity and alkalinity, but migrate to spawn in freshwater rivers each year. In this study, we measured the drinking rate over a 24 h period for naked carp exposed to saline-alkaline lake waters with salinities of 15 (L15) and 17 (L17). We also assessed the daily feed intakes of naked carp exposed to L15 and fresh water (FW). Additionally, we studied the daily expression of acid–base regulation and osmoregulation related genes and proteins in the intestine of naked carp exposed to saline-alkaline lake waters. Our results revealed that the drinking rate at night was significantly higher than in daytime when exposed to either L15 or L17, while feed intakes in daytime were significantly higher than at night. The relative expression of Na+/K+-ATPase α (NKA-α), solute carrier family members 26A6 (SLC26A6) and 4A4 (SLC4A4) in the intestine of naked carp exposed to L17 at night was higher than in daytime. Specifically, NKA-α mRNA expression at 4:00 was 7.22-fold and 5.63-fold higher than that at 10:00 and 16:00, respectively, and the expression at 22:00 was 11.29-fold and 8.80-fold higher than that at 10:00 and 16:00, respectively. Similarly, SLC26A6 mRNA expression was greatest at 22:00, exceeding that observed at 4:00, 10:00 and 16:00 by 3.59, 4.44 and 11.14-fold, respectively. Finally, the expression of NKA-α and SLC26A6 protein at the single cell level was also higher at night than during the day, which was 1.65-fold and 1.37-fold higher at 22:00 respectively compared to 16:00. Overall, the present findings revealed that naked carp drinks at night and feeds during the day, demonstrating that intestinal ion regulation exhibits a daily rhythm when exposed to high saline and alkaline lake water.

To solve the tracking drift caused by rotation, uneven illumination, and beyond the field of view in the moving process of the target with low contrast extension, a method of edge feature points matching is proposed in this paper. Specifically, feature points are extracted from image edges to improve the stability of feature points matching. In addition, combined Non-Local algorithm and improved Contrast Limited Adaptive Histogram Equalization algorithms are used to enhance the image. Experimental results show that this method has satisfactory performance, has good anti-rotation characteristics, can be stably tracked when the target reappears in the field of view and basically meets the real-time performance.

Visible and thermal modalities are strongly complementary in object signal representation. Using the two modalities simultaneously is beneficial to reduce the impact of illumination variation on pedestrian detection. To effectively utilize multimodal information, this paper proposes an anchor-free multimodal pedestrian algorithm. First, a modal feature fusion module is proposed, which executes modal fusion by decaying dense connections and combines convolution with the self-attention mechanism to account for local and global information between the modalities. Secondly, through the multiwindow global context module and the pyramid feature fusion module, a new feature pyramid network enhanced by global context information is proposed. On the visible-thermal pedestrian detection datasets KAIST, CVC-14 and LLVIP, the proposed method achieves 5.67%, 20.51% and 2.21% average miss rate respectively, which is better than the mainstream algorithms.

Abstract-In this paper, we propose a new saliency detection method based on graph. The method firstly uses SLIC to segment the image into a set of superpixels which are not overlapped, and regards these superpixels as nodes of the graph, then constructs a partly connected graph with these nodes. Secondly, the saliency values of these nodes are computed via absorbing Markov chain and manifold ranking, and a saliency map are obtained corresponding to each image. Finally, it uses a contrast stretching function to correct the above saliency map for improving the quality of image. Experimental results demonstrate that the proposed method can more easily distinguish salient objects from background, and performs better than some methods in terms of robustness and performance.

No abstract