One-dimensional time series classification has always been an important research direction, playing an irreplaceable role in various fields. With the rapid development of deep learning, most traditional time series classification methods have gradually been replaced by neural network-based classification methods. At present, in the field of time series classification, models that perform well are mostly based on Convolutional Neural Networks (CNNs), while models with the Transformer architecture, which have shown outstanding performance in natural language processing and computer vision, do not stand out. In order to change this situation, We have investigated the feasibility of training models based on a single Transformer architecture directly on small datasets without additional data processing. Furthermore, we propose a new model called CTCTime, which combines the Transformer architecture with CNNs to address one-dimensional time series classification problems. We compared CTCTime with 13 traditional algorithms on 44 datasets from the UCR archive and with 7 advanced methods on 85 datasets. The UCR datasets are classic datasets for one-dimensional time series classification tasks. The experimental results demonstrate its feasibility, accuracy, and scalability.

Abstract In this paper, a new approach to visual geo‐localization for natural environments is proposed. The digital elevation model (DEM) data in virtual space is rendered and construct a panoramic skyline database is constructed. By combining the skyline database with real‐world image data (used as the “queries” to be localized), visual geo‐localization is treated as a cross‐modal image retrieval problem for panoramic skyline images, creating a unique new visual geo‐localization benchmark for the natural environment. Specifically, the semantic segmentation model named LineNet is proposed, for skyline extractions from query images, which has proven to be robust to a variety of complex natural environments. On the aforementioned benchmarks, the fully automatic method is elaborated for large‐scale cross‐modal localization using panoramic skyline images. Finally, the compound index is delicately designed to reduce the storage space of the positioning global descriptors and improve the retrieval efficiency. Moreover, the proposed method is proven to outperform most state‐of‐the‐art methods.

Abstract The information unavailability of a global navigation satellite system (GNSS) for geo‐localization in many military and tourism applications implies the need to employ other applicable types of information, such as automatic image‐based location recognition. Unlike most existing localization methods that use GNSS information to locate an initial position, this paper proposes an automatic geo‐localization framework that does not require GNSS data. The proposed framework is a two‐stage pipeline that uses a query image and digital elevation model (DEM) data as input. The authors frame automatic geo‐localization without GNSS recordings as a skyline matching problem. By extracting the skyline from the DEM data and query images, the query image can be localized by matching the query skyline feature to the DEM skyline database. It has been demonstrated that this low‐cost approach can perform efficiently in mountainous or hilly areas to produce reliable localization results. The system was tested on 50 testing site points within a large‐scale area (China, 202.6 km 2 ), and an average position error of 43.13 m was detected within 4.5 s.

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The Cup-to-Disc Ratio (CDR) serves as the most important indicator for glaucoma screening and plays a significant role in clinical screening and early diagnosis of glaucoma. In general, obtaining CDR is subjected to measuring on manually or automatically segmented optic disc and cup. Despite great efforts have been devoted, obtaining CDR values automatically with high accuracy and robustness is still a great challenge due to the heavy overlap between optic cup and neuroretinal rim regions. In this paper, a direct CDR estimation method is proposed based on the well-designed semi-supervised learning scheme, in which CDR estimation is formulated as a general regression problem while optic disc/cup segmentation is cancelled. The method directly regresses CDR value based on the feature representation of optic nerve head via deep learning technique while bypassing intermediate segmentation. The scheme is a two-stage cascaded approach comprised of two phases: unsupervised feature representation of fundus image with a convolutional neural networks (MFPPNet) and CDR value regression by random forest regressor. The proposed scheme is validated on the challenging glaucoma dataset Direct-CSU and public ORIGA, and the experimental results demonstrate that our method can achieve a lower average CDR error of 0.0563 and a higher correlation of around 0.726 with measurement before manual segmentation of optic disc/cup by human experts. Our estimated CDR values are also tested for glaucoma screening, which achieves the areas under curve of 0.905 on dataset of 421 fundus images. The experiments show that the proposed method is capable of state-of-the-art CDR estimation and satisfactory glaucoma screening with calculated CDR value.

Glaucoma refers to a chronic disease of the eye that leads to vision loss that is irreversible, which is called ‘silent theft of sight’. Thus, an automatic glaucoma screening pipeline from optic disc (OD) localisation to glaucoma risk prediction is proposed in this study. The proposed pipeline consists of three main phases. Firstly, the OD is localised by morphological processing and sliding window methods. Secondly, a novel neural network which is in U‐shape and convolutional introduces concatenating path and fusion loss function is developed to split OD and optic cup (OC) at the same time. Thirdly, both clinical measurements including optic cup‐to‐disc ratio (CDR), neuroretinal rim related features, and hidden features including statistical moments, entropy and energy are combined to train glaucoma classifiers. According to the results of the experiment, the proposed segmentation network achieves the best performance on both OD and OC segmentation and the proposed CDR calculation method is capable of achieving the performance similar to that of ophthalmologist on CDR measurement. Besides, the authors’ glaucoma classification model can obtain the best performance on sensitivity and area under the curve score in comparison with the existing methods.

Automatic optic disc (OD) localisation and segmentation is still a great challenge in computer‐aided diagnosis and screening system. Here, a new OD segmentation algorithm is proposed based on the distinct features of OD in terms of its intensity and shape. The algorithm includes four stages: image preprocessing, image segmentation, ellipse fitting, and OD localisation and segmentation. In the preprocessing stage, the blood vessel in the input retinal image is removed by using the morphological operation and median filtering in HSL (hue–saturation–lightness) colour space. In the image segmentation and ellipse fitting stages, the fractional‐order Darwinian particle swarm optimisation algorithm is used to extract the brightest region, and the least‐squares optimisation is adopted to detect elliptical OD shape. Finally, the smooth OD borders are generated in the last stage. The proposed method is evaluated by the centroid difference, overlapping ratio, overlap score, and success indexes. Experimental results on the retinal images from DRION, MESSIDOR, ORIGA, and many other public databases demonstrate that the proposed method has superior performance, and may be a suitable tool for automated retinal image analysis.

Automatic retinal image registration is still a great challenge in computer aided diagnosis and screening system. In this paper, a new retinal image registration method is proposed based on the combination of blood vessel segmentation and scale invariant feature transform (SIFT) feature. The algorithm includes two stages: retinal image segmentation and registration. In the segmentation stage, the blood vessel is segmented by using the guided filter to enhance the vessel structure and the bottom-hat transformation to extract blood vessel. In the registration stage, the SIFT algorithm is adopted to detect the feature of vessel segmentation image, complemented by using a random sample consensus (RANSAC) algorithm to eliminate incorrect matches. We evaluate our method from both segmentation and registration aspects. For segmentation evaluation, we test our method on DRIVE database, which provides manually labeled images from two specialists. The experimental results show that our method achieves 0.9562 in accuracy (Acc), which presents competitive performance compare to other existing segmentation methods. For registration evaluation, we test our method on STARE database, and the experimental results demonstrate the superior performance of the proposed method, which makes the algorithm a suitable tool for automated retinal image analysis.

Existing view-invariant gait recognition methods encounter difficulties due to limited number of available gait views and varying conditions during training. This paper proposes gait partial similarity matching that assumes a 3D object shares common view surfaces in significantly different views. Detecting such surfaces aids the extraction of gait features from multiple views; 3D parametric body models are morphed by pose and shape deformation from a template model using 2D gait silhouette as observation. The gait pose is estimated by a level set energy cost function from silhouettes including incomplete ones. Body shape deformation is achieved via Laplacian deformation energy function associated with inpainting gait silhouettes. Partial gait silhouettes in different views are extracted by gait partial region of interest elements selection and re-projected onto 2D space to construct partial gait energy images. A synthetic database with destination views and multi-linear subspace classifier fused with majority voting is used to achieve arbitrary view gait recognition that is robust to varying conditions. Experimental results on CMU, CASIA B, TUM-IITKGP, AVAMVG, and KY4D data sets show the efficacy of the propose method.

We propose a method to recognize Chinese traffic police gesture in complex scene for intelligent vehicle. The gesture recognition is made by integrated nonparametric background modeling with human pose estimation. Firstly, dark channel prior and kernel density estimation are used to extract police's torso and arms from complex traffic environment as foreground region. Then, the coordinates of pixels in the upper and lower arms are determined by using max-covering scheme, which is based on a key observation that body part tiles maximally cover the foreground region and satisfy body plan. Finally, some typical police gestures can be recognized by rotation joint angle. The experimental results show that this method can obtain favorable results on a number of gesture sequences of traffic police.