In this paper, we rethink our earlier work on self-attention based crack segmentation, and propose an upgraded CrackFormer network (CrackFormer-II) for pavement crack segmentation, instead of only for fine-grained crack-detection tasks. This work embeds novel Transformer encoder modules into a SegNet-like encoder-decoder structure, where the basic module is composed of novel Transformer encoder blocks with effective relative positional embedding and long range interactions to extract efficient contextual information from feature-channels. Further, fusion modules of scaling-attention are proposed to integrate the results of each respective encoder and decoder block to highlight semantic features and suppress non-semantic ones. Moreover, we update the Transformer encoder blocks enhanced by the local feed-forward layer and skip-connections, and optimize the channel configurations to compress the model parameters. Compared with the original CrackFormer, the CrackFormer-II is trained and evaluated on more general crack datasets. It achieves higher accuracy than the original CrackFormer, and the state-of-the-art (SOTA) method with $6.7$ $\times$ fewer FLOPs and $6.2$ $\times$ fewer parameters, and its practical inference speed is comparable to most classical CNN models. The experimental results show that it achieves the F-measures on Optimal Dataset Scale (ODS) of 0.912, 0.908, 0.914 and 0.869, respectively, on the four benchmarks. Codes are available at https://github.com/LouisNUST/CrackFormer-II.

Road segmentation from remote sensing images is a challenging task in capturing weak, long, and irregular road features due to the limited connectivity-preserving modeling capability. In this work, we proposed a U-shaped Fourier-Deformable Convolution Network (FDNet) for road segmentation, which integrates the merits of deformable convolutions and Fourier convolutions compactly. Specifically, a saliency-aware deformable convolution (SD-Conv) layer is proposed for tracing salient road features based on an iterative dynamic offset learning mechanism to grasp extremely tender and weak road objects. Meanwhile, a lightweight global feature extracting module based on spectral convolutions, namely the adaptive Fourier convolution (AF-Conv) layer, is adopted to learn long-range dependency to extract long and continuous road structures. The proposed SD-Conv layer worked in parallel with the AF-Conv layer to construct a basic and compact block to build the U-shaped FDNet model for road segmentation. Furthermore, to maintain the continuity of road objects in complex road conditions, we introduced a topology-oriented loss function based on the Hausdorff distance on the persistence diagram of segmented results, and further combined with softDice loss components for fully supervised training. Our FDNet has been trained and evaluated on two benchmarks, and experimental results show that FDNet achieved state-of-the-art (SOTA) performance. Specifically, it achieved 80.34% on accuracy, 88.42% on precision, and 84.70% on mIoU, respectively, on the Massachusetts dataset, and achieved 99.05% on accuracy, 89.21% on precision, 88.61% on recall, and 81.37% on mIoU, respectively, on the DeepGlobe dataset, outperforming most previous methods on both datasets. Codes are available at: https://github.com/zhoucharming/FDNet.

Object detection, as one of the most important environment perception tasks for traffic safety in intelligent transportation systems, has been widely investigated recently. However, most of the researches focus on the fully supervised scenario, and inevitably lead to model failure. With the continuous development of Zero-Shot Learning (ZSL) models, Generalized Zero-Shot Detection (GZSD) has attracted great attention due to its ability of detecting unseen objects. Many researchers tend to map the detected visual features to semantic attributes and then separate seen and unseen domains during inference. But they have ignore that the generative methods generally have higher performance than these visual-semantic mapping methods, and they have been confirmed from previous GZSL methods. In order to make up for the vacancy of GZSD in the generative methods, we propose an idea of using curriculum learning to generate more precise unseen visual features. And with the excellent performance of WGAN-based method in sample synthesis, we realize the function of using semantics to generate visual features for unseen domains. In addition, we also adopt part of the idea of meta-learning to progressively correct the capability of the generator for better mitigating domain shift problem during the generation process. Through the above ideas, we can detect both seen and unseen bounding boxes and classify them accurately, by combining with the excellent detection ability of Faster-RCNN. Extensive experimental results on two popular datasets, i.e., MSCOCO and KITTI, show that our proposed method can outperform the state-of-the-art methods.

Tracking maneuvering targets is a challenging problem for sensors because of the unpredictability of the target’s motion. Unlike classical statistical modeling of target maneuvers, a simultaneous optimization and feedback learning algorithm for maneuvering target tracking based on the Elman neural network (ENN) is proposed in this paper. In the feedback strategy, a scale factor is learnt to adaptively tune the dynamic model’s error covariance matrix, and in the optimization strategy, a corrected component of the state vector is learnt to refine the final state estimation. These two strategies are integrated in an ENN-based unscented Kalman filter (UKF) model called ELM-UKF. This filter can be trained online by the filter residual, innovation and gain matrix of the UKF to simultaneously achieve maneuver feedback and an optimized estimation. Monte Carlo experiments on synthesized radar data showed that our algorithm had better performance on filtering precision compared with most maneuvering target tracking algorithms.

Segmentation of roads in remote sensing images is a challenging task due to the inhomogeneous intensity, non-consistent contrast, and very cluttered background in remote sensing images. Recent approaches, mostly relying on convolutions or self-attention, make it difficult to extract weak and continuous road objects. Fourier neural operators provide another novel mechanism for capturing long-range and fine-grained features beyond self-attention. Based on it, we propose an adaptive Fourier convolution network (AFCNet) on the spatial-spectral domain for road segmentation in this paper. The AFCNet is built on the pipeline of the classical U-Net model and its core is the proposed Fourier neural encoder (FNE), which is built on a feed-forward layer and a flexible Fourier convolutional structure composed of Fourier-domain pooling layers, asymmetric convolutions, squeeze-excitation inspired self-attention and adaptive multiscale fusion layers. Furthermore, we combine the FNE and bottleneck in ResNet to form a hybrid global-local feature representation scheme to capture the long and weak road objects in remote sensing images. The experiments on two public datasets, the Massachusetts Roads and DeepGlobe Road Datasets, have shown that AFCNet worked with fewer parameters and outperformed most previous methods in terms of accuracy, precision, recall, and mean intersection over union (mIoU), etc.