In this paper, we propose an efficient method to separate the diffuse and specular reflection components from a single image. The method is built on the observation that, for diffuse pixels, the intensity ratios between the maximum values and range values (maximums minus minimums) are independent of surface geometry. The specular fractions of the image pixels can then be computed by using the intensity ratio. For textured surfaces, image pixels are classified into clusters by constructing a pseudo-chromaticity space, and the intensity ratio of each cluster is robustly estimated. Unlike existing techniques, the proposed method works in a pixel-wise manner, without specular pixel identification and any local interaction. Experimental results show that the proposed method runs $4\times$ faster than the state of the art and produces improved accuracy in specular highlight removal.

Recognizing places using Lidar in large-scale environments is challenging due to the sparse nature of point cloud data. In this letter we present BVMatch, a Lidar-based frame-to-frame place recognition framework, that is capable of estimating 2D relative poses. Based on the assumption that the ground area can be approximated as a plane, we uniformly discretize the ground area into grids and project 3D Lidar scans to bird's-eye view (BV) images. We further use a bank of Log-Gabor filters to build a maximum index map (MIM) that encodes the orientation information of the structures in the images. We analyze the orientation characteristics of MIM theoretically and introduce a novel descriptor called bird's-eye view feature transform (BVFT). The proposed BVFT is insensitive to rotation and intensity variations of BV images. Leveraging the BVFT descriptors, we unify the Lidar place recognition and pose estimation tasks into the BVMatch framework. The experiments conducted on three large-scale datasets show that BVMatch outperforms the state-of-the-art methods in terms of both recall rate of place recognition and pose estimation accuracy.

Pedestrian detection plays a critical role in computer vision as it contributes to ensuring traffic safety. Existing methods that rely solely on RGB images suffer from performance degradation under low-light conditions due to the lack of useful information. To address this issue, recent multispectral detection approaches have combined thermal images to provide complementary information and have obtained enhanced performances. Nevertheless, few approaches focus on the negative effects of false positives (FPs) caused by noisy fused feature maps. Different from them, we comprehensively analyze the impacts of FPs on detection performance and find that enhancing feature contrast can significantly reduce these FPs. In this article, we propose a novel target-aware fusion strategy for multispectral pedestrian detection, named TFDet. The target-aware fusion strategy employs a fusion-refinement paradigm. In the fusion phase, we reveal the parallel- and cross-channel similarities in RGB and thermal features and learn an adaptive receptive field to collect useful information from both features. In the refinement phase, we use a segmentation branch to discriminate the pedestrian features from the background features. We propose a correlation-maximum loss function to enhance the contrast between the pedestrian features and background features. As a result, our fusion strategy highlights pedestrian-related features and suppresses unrelated ones, generating more discriminative fused features. TFDet achieves state-of-the-art performance on two multispectral pedestrian benchmarks, KAIST and LLVIP, with absolute gains of 0.65% and 4.1% over the previous best approaches, respectively. TFDet can easily extend to multiclass object detection scenarios. It outperforms the previous best approaches on two multispectral object detection benchmarks, FLIR and M3FD, with absolute gains of 2.2% and 1.9%, respectively. Importantly, TFDet has comparable inference efficiency to the previous approaches and has remarkably good detection performance even under low-light conditions, which is a significant advancement for ensuring road safety. The code will be made publicly available at https://github.com/XueZ-phd/TFDet.git.

Out-of-focus blur is a common image degradation phenomenon that occurs in case of lens defocusing. The out-of-focus blur kernel is usually modeled as a Gaussian function or a uniform disk in previous work. In this paper, we propose that it can be more accurately depicted using the generalized Gaussian (GG) function. This is motivated by the theoretical analysis of the out-of-focus blur and the practical observation of real blur kernels. We show that as the out-of-focus blur kernels are of specific shapes, the GG function can be further simplified to a single-parameter model. We estimate the parameter of the GG blur kernel from image patches containing step edges, and obtain the clear image by non-blind image deblurring. Experimental results validate that the proposed GG blur kernel estimation algorithm outperforms the state-of-the-art ones deploying either parametric (disk and Gaussian) or nonparametric kernels, and consequently benefits the image deblurring process.

For dielectric inhomogeneous objects, the perceived reflections are the linear combinations of diffuse and specular reflection components. Specular reflection plays an important role in the fields of image analysis, pattern recognition, and scene synthesis. Several methods for the separation of the diffuse and the specular reflection components have been presented based on image segmentation or local interaction of neighboring pixels. We propose a simple and effective method for specularity removal in a single image on the level of each individual pixel. The chromaticity of diffuse reflection is approximately estimated by employing the concept of modified specular-free image, and the specular component is adjusted according to the criterion of smooth color transition along the boundary of diffuse and specular regions. Experimental results indicate that the proposed method is promising when compared with other state-of-the-art techniques, in both separation accuracy and running speed.

In multispectral imaging, Wiener estimation is widely adopted for the reconstruction of spectral reflectance. We propose an improved reflectance reconstruction method by adaptively selecting training samples for the autocorrelation matrix calculation in Wiener estimation, without a prior knowledge of the spectral information of the samples being imaged. The performance of the proposed adaptive Wiener estimation and the traditional method are compared in the cases of different channel numbers and noise levels. Experimental results show that the proposed method outperforms the traditional method in terms of both spectral and colorimetric prediction errors when the imaging channel number is 7 or less. When the imaging system consists of 11 or more channels, the color accuracy of the proposed method is slightly better than or becomes close to that of the traditional method.