Many studies utilize dual-pixel (DP) sensor phase characteristics for various applications, such as depth estimation and deblurring. However, since the DP image features are entirely determined by the camera hardware, DP-depth paired datasets are very scarce, especially when performing depth estimation on customized cameras. To overcome this, studies simulate DP images using ideal optical system models. However, these simulations often violate real optical propagation laws, leading to poor generalization to real DP data. To address this, we investigate the domain gap between simulated and real DP data, and propose solutions using the Simulating DP images from ray tracing (Sdirt) scheme. The Sdirt generates realistic DP images via ray tracing and integrates them into the depth estimation training pipeline. Experimental results show that models trained with Sdirt-simulated images generalize better to real DP data. The code and collected datasets will be available at github.com/LinYark/Sdirt

In this paper, we propose a fence recognition method based on the ENet (Efficient neural Network) segmentation network to address the problems of traditional segmentation networks, which have poor performance in recognizing fences with a large range of scale variations and hollow structures.Firstly, a multi-scale attention fusion ENet segmentation network is designed, which is trained using the fence with obvious color features.Then, a morphological algorithm is used to process the predicted image to restore the fence segmentation results.The designed multi-scale attention fusion segmentation network performs better on fence datasets than traditional methods.In addition, the activation function Leaky_Relu6 further enhances the stability and generalization ability of the network.The experiments are conducted on 540 fence images from different construction sites, and the computed IoU is 90%.The processing speed is about 28 frames per second.The experimental results show that our proposed network outperforms traditional segmentation algorithms in fence recognition performance, and achieves robustness in different construction scenarios while meeting the requirements of both accuracy and speed.

Neuron tracing from optical image is critical in understanding brain function in diseases. A key problem is to trace discontinuous filamentary structures from noisy background, which is commonly encountered in neuronal and some medical images. Broken traces lead to cumulative topological errors, and current methods were hard to assemble various fragmentary traces for correct connection. In this paper, we propose a graph connectivity theoretical method for precise filamentary structure tracing in neuron image. First, we build the initial subgraphs of signals via a region-to-region based tracing method on CNN predicted probability. CNN technique removes noise interference, whereas its prediction for some elongated fragments is still incomplete. Second, we reformulate the global connection problem of individual or fragmented subgraphs under heuristic graph restrictions as a dynamic linear programming function via minimizing graph connectivity cost, where the connected cost of breakpoints are calculated using their probability strength via minimum cost path. Experimental results on challenging neuronal images proved that the proposed method outperformed existing methods and achieved similar results of manual tracing, even in some complex discontinuous issues. Performances on vessel images indicate the potential of the method for some other tubular objects tracing.

BACKGROUND: Soma localization is an important step in computational neuroscience to map neuronal circuits. However, locating somas from large-scale and complicated datasets is challenging. The challenges primarily originate from the dense distribution of somas, the diversity of soma sizes and the inhomogeneity of image contrast. RESULTS: We proposed a novel localization method based on density-peak clustering. In this method, we introduced two quantities (the local density ρ of each voxel and its minimum distance δ from voxels of higher density) to describe the soma imaging signal, and developed an automatic algorithm to identify the soma positions from the feature space (ρ, δ). Compared with other methods focused on high local density, our method allowed the soma center to be characterized by high local density and large minimum distance. The simulation results indicated that our method had a strong ability to locate the densely positioned somas and strong robustness of the key parameter for the localization. From the analysis of the experimental datasets, we demonstrated that our method was effective at locating somas from large-scale and complicated datasets, and was superior to current state-of-the-art methods for the localization of densely positioned somas. CONCLUSIONS: Our method effectively located somas from large-scale and complicated datasets. Furthermore, we demonstrated the strong robustness of the key parameter for the localization and its effectiveness at a low signal-to-noise ratio (SNR) level. Thus, the method provides an effective tool for the neuroscience community to quantify the spatial distribution of neurons and the morphologies of somas.