Make and model recognition (MMR) of vehicles plays an important role in automatic vision-based systems. This paper proposes a novel deep learning approach for MMR using the SqueezeNet architecture. The frontal views of vehicle images are first extracted and fed into a deep network for training and testing. The SqueezeNet architecture with bypass connections between the Fire modules, a variant of the vanilla SqueezeNet, is employed for this study, which makes our MMR system more efficient. The experimental results on our collected large-scale vehicle datasets indicate that the proposed model achieves 96.3% recognition rate at the rank-1 level with an economical time slice of 108.8 ms. For inference tasks, the deployed deep model requires less than 5 MB of space and thus has a great viability in real-time applications.

Human action monitoring can be advantageous to remotely monitor the status of patients or elderly person for intelligent healthcare. Human action recognition enables efficient and accurate monitoring of human behaviors, which can exhibit multifaceted complexity attributed to disparities in viewpoints, personality, resolution and motion speed of individuals, etc. The spatial-temporal information plays an important role in the human action recognition. In this paper, we proposed a novel deep learning architecture named as recurrent 3D convolutional neural network (R3D) to extract effective and discriminative spatial-temporal features to be used for action recognition, which enables the capturing of long-range temporal information by aggregating the 3D convolutional network entries to serve as an input to the LSTM (Long Short-Term Memory) architecture. The 3D convolutional network and LSTM are two effective methods for extracting the temporal information. The proposed R3D network integrated these two methods by sharing a shared 3D convolutional network in sliding windows on video streaming to capturing short-term spatial-temporal features into the LSTM. The output features of LSTM encapsulate the long-range spatial-temporal information representing high-level abstraction of the human actions. The proposed algorithm is compared to traditional and the-state-of-the-art and deep learning algorithms. The experimental results demonstrated the effectiveness of the proposed system, which can be used as smart monitoring for remote healthcare.

Coronary heart disease is one of the most serious health problems in the world nowadays. By segmenting and examining the coronary arteries in medical images, we can find artery stenosis and plaque, which are the main causes of this certain disease. Segmenting coronary arteries manually is time-consuming and subjective, and the traditional segmentation method requires a good initial point, which is also difficult to apply for the 3D coronary computed tomography angiography (CTA) data. In this paper, we propose a joint framework for coronary CTA segmentation based on deep learning and traditional level set method. A 3D fully convolutional network (FCN) is used to learn the 3D semantic features of coronary arteries, which provides an excellent initial point for the traditional level set. Moreover, an attention gate is added to the entire network, aiming to enhance the vessels and suppress irrelevant regions. The output of 3D FCN with attention gate is optimized by the level set to smooth the boundary to better fit the ground truth segmentation. The proposed algorithm is evaluated by the Jaccard index (JI) and the Dice similarity coefficient (DSC) scores. The experimental results show that the proposed framework provides significant better segmentation results than the vanilla 3D FCN intuitively and quantitively.

6G network enables the rapid connection of autonomous vehicles, the generated internet of vehicles establishes a large-scale point cloud, which requires automatic point cloud analysis to build an intelligent transportation system in terms of the 3D object detection and segmentation. Recently, a great variety of deep convolution networks have been proposed for 3D data analysis, making significant progress in the application of deep learning in 3D computer vision. Inspired by the application of transformer network in 2D computer visual tasks, and in order to increase the expression ability of local fine-grained features, we propose an effective local feature transformer network to learn local feature information and correlations between point clouds. Our network is adaptive to the arrangement of set elements through transformer module, so it is suitable for the feature extraction of local point clouds. In addition, experimental results demonstrate that our LFT-network outperforms the state-of-the-art in 3D model classification tasks on ModelNet40 dataset and segmentation tasks on S3DIS dataset.

Depth estimation from a camera is an important task for 3D perception. Recently, without using the labeled ground truth of depth map, a self-supervised deep learning network can use relative pose to synthesize the target image from the reference image, and the photometric error between synthesized reference image and real one is used as self-supervisory signal. In this paper, we propose a novel self-supervised depth estimation network, which takes advantage of the quadtree constraint to optimize the depth estimation network. Based on the quadtree constraint, the photometric loss and depth loss of quadtree are proposed. In order to solve the problem that multiple depth values in repeated structures and uniform texture regions can cause relatively low photometric loss, we use quadtree-based photometric loss, which calculates the averaged photometric loss in quadtree blocks instead of the pixel-wise loss. For the problem of imbalanced depth distribution, we use quadtree depth loss, which constrains the depth inconsistency within quadtree blocks. The depth estimation network is composed of deep fusion module and cross-layer feature fusion module, which can better extract the feature information of RGB image and sparse keypoints depths, and makes full use of the detail information of the shallow feature map and the semantic information of the deep feature map to enrich the feature information extraction. Experimental results demonstrate that our method outperforms the state-of-the-art approaches of depth estimation.