Compared to other biometrics, gait is difficult to conceal and has the advantage of being unobtrusive. Inertial sensors, such as accelerometers and gyroscopes, are often used to capture gait dynamics. These inertial sensors are commonly integrated into smartphones and are widely used by the average person, which makes gait data convenient and inexpensive to collect. In this paper, we study gait recognition using smartphones in the wild. In contrast to traditional methods, which often require a person to walk along a specified road and/or at a normal walking speed, the proposed method collects inertial gait data under unconstrained conditions without knowing when, where, and how the user walks. To obtain good person identification and authentication performance, deep-learning techniques are presented to learn and model the gait biometrics based on walking data. Specifically, a hybrid deep neural network is proposed for robust gait feature representation, where features in the space and time domains are successively abstracted by a convolutional neural network and a recurrent neural network. In the experiments, two datasets collected by smartphones for a total of 118 subjects are used for evaluations. The experiments show that the proposed method achieves higher than 93.5% and 93.7% accuracies in person identification and authentication, respectively.

Deep Learning-Based Gait Recognition Using Smartphones in the Wild

The search for predictive models that generalize to the long tail of sensor inputs is the central difficulty when developing data-driven models for autonomous vehicles. In this paper, we use lane detection to study modeling and training techniques that yield better performance on real world test drives. On the modeling side, we introduce a novel fully convolutional model of lane detection that learns to decode lane structures instead of delegating structure inference to post-processing. In contrast to previous works, our convolutional decoder is able to represent an arbitrary number of lanes per image, preserves the polyline representation of lanes without reducing lanes to polynomials, and draws lanes iteratively without requiring the computational and temporal complexity of recurrent neural networks. Because our model includes an estimate of the joint distribution of neighboring pixels belonging to the same lane, our formulation includes a natural and computationally cheap definition of uncertainty. On the training side, we demonstrate a simple yet effective approach to adapt the model to new environments using unsupervised style transfer. By training FastDraw to make predictions of lane structure that are invariant to low-level stylistic differences between images, we achieve strong performance at test time in weather and lighting conditions that deviate substantially from those of the annotated datasets that are publicly available. We quantitatively evaluate our approach on the CVPR 2017 Tusimple lane marking challenge, difficult CULane datasets [29], and a small labeled dataset of our own and achieve competitive accuracy while running at 90 FPS.

/pdf/fastdraw-addressing-the-long-tail-of-lane-detection-by-in37vjpw27.pdf

FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network

Perception techniques for autonomous driving should be adaptive to various environments. In the case of traffic line detection, an essential perception module, many condition should be considered, such as number of traffic lines and computing power of the target system. To address these problems, in this paper, we propose a traffic line detection method called Point Instance Network (PINet); the method is based on the key points estimation and instance segmentation approach. The PINet includes several stacked hourglass networks that are trained simultaneously. Therefore the size of the trained models can be chosen according to the computing power of the target environment. We cast a clustering problem of the predicted key points as an instance segmentation problem; the PINet can be trained regardless of the number of the traffic lines. The PINet achieves competitive accuracy and false positive on the TuSimple and Culane datasets, popular public datasets for lane detection. Our code is available at this https URL

Key Points Estimation and Point Instance Segmentation Approach for Lane Detection.

We address the curve lane detection problem which poses more realistic challenges than conventional lane detection for better facilitating modern assisted/autonomous driving systems. Current hand-designed lane detection methods are not robust enough to capture the curve lanes especially the remote parts due to the lack of modeling both long-range contextual information and detailed curve trajectory. In this paper, we propose a novel lane-sensitive architecture search framework named CurveLane-NAS to automatically capture both long-ranged coherent and accurate short-range curve information. It consists of three search modules: a) a feature fusion search module to find a better fusion of the local and global context for multi-level hierarchy features; b) an elastic backbone search module to explore an efficient feature extractor with good semantics and latency; c) an adaptive point blending module to search a multi-level post-processing refinement strategy to combine multi-scale head prediction. Furthermore, we also steer forward to release a more challenging benchmark named CurveLanes for addressing the most difficult curve lanes. It consists of 150K images with 680K labels (The new dataset can be downloaded at http://www.noahlab.com.hk/opensource/vega/#curvelanes). Experiments on the new CurveLanes show that the SOTA lane detection methods suffer substantial performance drop while our model can still reach an 80+% F1-score. Extensive experiments on traditional lane benchmarks such as CULane also demonstrate the superiority of our CurveLane-NAS, e.g. achieving a new SOTA 74.8% F1-score on CULane.

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending

Modern lane detection methods have achieved remarkable performances in complex real-world scenarios, but many have issues maintaining real-time efficiency, which is important for autonomous vehicles. In this work, we propose LaneATT: an anchor-based deep lane detection model, which, akin to other generic deep object detectors, uses the anchors for the feature pooling step. Since lanes follow a regular pattern and are highly correlated, we hypothesize that in some cases global information may be crucial to infer their positions, especially in conditions such as occlusion, missing lane markers, and others. Thus, this work proposes a novel anchor-based attention mechanism that aggregates global information. The model was evaluated extensively on three of the most widely used datasets in the literature. The results show that our method outperforms the current state-of-the-art methods showing both higher efficacy and efficiency. Moreover, an ablation study is performed along with a discussion on efficiency trade-off options that are useful in practice.

Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection

Lane detection in driving scenes is an important module for autonomous vehicles and advanced driver assistance systems. In recent years, many sophisticated lane detection methods have been proposed. However, most methods focus on detecting the lane from one single image, and often lead to unsatisfactory performance in handling some extremely-bad situations such as heavy shadow, severe mark degradation, serious vehicle occlusion, and so on. In fact, lanes are continuous line structures on the road. Consequently, the lane that cannot be accurately detected in one current frame may potentially be inferred out by incorporating information of previous frames. To this end, we investigate lane detection by using multiple frames of a continuous driving scene, and propose a hybrid deep architecture by combining the convolutional neural network (CNN) and the recurrent neural network (RNN). Specifically, information of each frame is abstracted by a CNN block, and the CNN features of multiple continuous frames, holding the property of time-series, are then fed into the RNN block for feature learning and lane prediction. Extensive experiments on two large-scale datasets demonstrate that, the proposed method outperforms the competing methods in lane detection, especially in handling difficult situations.

Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks

Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks

Cracks in tunnel linings are the most common tunnel defects. As early indicators of structural deterioration, cracks represent critical problems for the safety of tunnels. Several mobile tunnel inspection systems (MTISs) have been developed for tunnel crack inspection. However, due to the weak signals of cracks, these MTISs require considerable exposure time to capture high-quality tunnel images, necessitating a low travel speed. Meanwhile, traditional crack detection methods encounter difficulties in processing tunnel crack images because of their low contrast and poor continuity. To overcome these challenges, this study presents a new MTIS for fast tunnel crack inspection that consists of a novel mobile imaging module and an automatic crack detection module. The imaging module is composed of an array of high-resolution charge-coupled device (CCD) cameras, a mobile laser scanner, and a lighting array. The core of the crack detection module is a novel lightweight convolutional neural network (CNN) designed for efficient tunnel crack detection, with an effective spatial constraint strategy to guarantee crack continuity. We collected a new tunnel crack dataset consisting of 1,218 images using our mobile imaging module at a driving speed of 80 km/h. Comprehensive experiments were conducted on this dataset to evaluate the performance of our proposed network. The results demonstrate that the presented CNN can effectively detect tunnel cracks with state-of-the-art performance, achieving an F1-score greater than 0.88 and an inference speed of 17 FPS with only 3.4M model parameters. The code and data are available at https://github.com/urban-informatics/LinkCrack.

Automatic Tunnel Crack Inspection Using an Efficient Mobile Imaging Module and a Lightweight CNN

Cracks are the most common defect on the surface of tunnels, which potentially brings threaten to the safety of the tunnel and the running vehicles. Timely repairing of the crack is of critical importance. In the past two decades, various vehicle platforms have been developed on the purpose of efficient crack detection and maintenance. With these platforms, images can be captured in a traffic speed, and automatic methods can be developed for fast crack localization. However, for image-based crack detection, traditional methods often meet difficulties in handling cracks with low contrast and poor continuity. In this paper, deep learning based techniques are exploited for feature learning and representation for crack detection. A novel deep neural network is presented for pixel-level crack recognition. Hierarchical features in different stages of the convolution are fused together to overcome the influence of noise and a spatial constraint placed on the target pixels is used to guarantee the crack continuity. In the experiment, a tunnel crack dataset is constructed for performance evaluation. Experimental results demonstrate the effectiveness of proposed method.

Deep Learning with Spatial Constraint for Tunnel Crack Detection

Text detection in the wild has been a popular research topic, and previous approaches to scene text detection have achieved promising performances across various benchmarks. In general, these methods use a large number of labels with precise character positions as training data. However, accurate annotation of large amounts of training data is a challenge. On the other hand, image-level annotation can be quickly obtained from rich media in a tag retrieval manner. Therefore it is essential to investigate how to improve the performance of strongly supervised text detection models through image-level annotation data. In this work, we propose a training framework for collaborative learning of a weakly supervised text classification network and a strongly supervised text detection network. The collaborative learning of the two sub-task networks is achieved by constraining the consistency of the two networks at the perceptual level. Experiments on standard data set ICDAR2015 show that the framework can significantly improve the performance of the strongly supervised text detection network by training using image-level annotation data.

Yuanhao Yue

Papers

Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks

Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks

Automatic Tunnel Crack Inspection Using an Efficient Mobile Imaging Module and a Lightweight CNN

Deep Learning with Spatial Constraint for Tunnel Crack Detection

Collaborative Learning Network for Scene Text Detection