Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the valuable features and aggregate contextual information, especially the interrelationships between lane lines and other regions of the images in continuous frames. To fill this research gap and upgrade lane detection performance, this paper proposes a pipeline consisting of self pre-training with masked sequential autoencoders and fine-tuning with customized PolyLoss for the end-to-end neural network models using multi-continuous image frames. The masked sequential autoencoders are adopted to pre-train the neural network models with reconstructing the missing pixels from a random masked image as the objective. Then, in the fine-tuning segmentation phase where lane detection segmentation is performed, the continuous image frames are served as the inputs, and the pre-trained model weights are transferred and further updated using the backpropagation mechanism with customized PolyLoss calculating the weighted errors between the output lane detection results and the labeled ground truth. Extensive experiment results demonstrate that, with the proposed pipeline, the lane detection model performance on both normal and challenging scenes can be advanced beyond the state-of-the-art, delivering the best testing accuracy (98.38%), precision (0.937), and F1-measure (0.924) on the normal scene testing set, together with the best overall accuracy (98.36%) and precision (0.844) in the challenging scene test set, while the training time can be substantially shortened.

Accurate and reliable lane detection is vital for the safe performance of lane-keeping assistance and lane departure warning systems. However, under certain challenging circumstances, it is difficult to get satisfactory performance in accurately detecting the lanes from one single image as mostly done in current literature. Since lane markings are continuous lines, the lanes that are difficult to be accurately detected in the current single image can potentially be better deduced if information from previous frames is incorporated. This study proposes a novel hybrid spatial–temporal (ST) sequence-to-one deep learning architecture. This architecture makes full use of the ST information in multiple continuous image frames to detect the lane markings in the very last frame. Specifically, the hybrid model integrates the following aspects: (a) the single image feature extraction module equipped with the spatial convolutional neural network; (b) the ST feature integration module constructed by ST recurrent neural network; (c) the encoder–decoder structure, which makes this image segmentation problem work in an end-to-end supervised learning format. Extensive experiments reveal that the proposed model architecture can effectively handle challenging driving scenes and outperforms available state-of-the-art methods.

The booming bike-sharing business provides great convenience to people's daily travel and brings notable change to city traffic. Meanwhile, few studies have analyzed the basis patterns of sharing-bikes and their influence on the traffic using empirical data. In this paper, we investigate the data provided by one of the leading bike-sharing companies. The city is gridded into regular rectangle regions using a geohash algorithm, and the starting and ending region of bike journeys are given. We modeled the macro travel patterns of sharing bikes in a spatial-temporal manner and used the non-negative matrix factorization (NFM) method to obtain the basis collective patterns. The patterns show that, different from other modes of shared mobility like ride-sharing, the trip characteristics of bike-sharing could be approximately described by a linear combination of three basis patterns, and bike-sharing mainly serves for the first/last mile short-distance travel around transport hubs, i.e., subway stations. Our findings are helpful for policy makers to better understand the dynamics patterns and influence of sharing-bikes, and to make better arrangements towards facility building and other bike policies.

The rapid growth of internet based ride-sharing brings great changes to residents' travel and city traffic. However, few studies had employed empirical data to examine the unique travel patterns of internet based ride-sharing trips. In this paper, we compare taxi trip records and internet based ride-sharing trip records provided by DiDi company. Results reveal many interesting findings that had never been reported before. From the viewpoint of service patterns, ride-sharing mainly increases supplies in hot areas and peak hours. By applying a non-negative matrix factorization method, we find that ride-sharing principally serves as an approach for commuting. So, as an effective supplement to traditional taxi service, it regulates spatial and temporal supply-demand imbalance, especially during morning and evening rush periods. From the viewpoint of individual behavior patterns, we use a clustering method to identify two kinds of internet based ride-sharing drivers. The first kind of drivers usually provides ride-sharing along daily home-work commuting. Trips served by these drivers have relatively constant origin-designation (OD) pairs. The second kind of drivers does not serve regularly and roams around the city even in working hours. Therefore, there are no constant OD pairs in their ride-sharing trips. Counterintuitively, we find that home-work commuting drivers account for only a small part of total drivers and they only serve a small number of commuting trips. In addition, internet based ride-sharing is not just traditional hitchhiking worked through mobile internet. We find that internet based ride-sharing drivers intend to make long distance trips, and they intend to detour further to pick up or drop off passengers than traditional hitchhike drivers since they are paid. All these findings are helpful for policy makers at all levels to make informed decisions about deployment of internet based ride-sharing service. This paper also verifies that big data analytics is particularly useful and powerful in the analysis of ride-sharing and taxi service patterns.

The records generated by taxicabs which are equipped with GPS devices is of vital importance for studying human mobility behavior, however we are focusing on taxi drivers' operation patterns in this paper. We identify a group of valuable characteristics, which are simple but effective, through large scale drivers' behavior in a complex metropolis environment. Based on the daily operations of 31,000 taxi drivers in New York City which covers over 14 million of trip records during Jan 1 to Jan 31 in 2013, we classify drivers into top, ordinary and low income groups according to monthly working load, daily income and daily ranking. Then, we apply big data analysis and visualization methods to compare the different characteristics among top, ordinary and low income drivers in selecting of working time, working area as well as driving routes. The results verify that top drivers do have special operation tactics to help themselves serve more passengers, travel faster thus make more money per unit time. This research provides new possibilities for fully utilizing the information obtained from urban taxicab data for estimating human behavior, which is not only very useful for individual taxicab driver but also to those policy-makers in city authorities.