Ridesharing car detection by transfer learning

Wang, Leye; Geng, Xu; Ma, Xiaojuan; Zhang, Daqing; Yang, Qiang

doi:10.1016/j.artint.2018.12.008

Cited by 36 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each iteration, the loss value and correct value can be counted, the model with the highest correct value is saved, and then the next iteration of training is conducted. In transfer learning, the weights of all network layers, except the last fully connected layer, are frozen, and only the fully connected layer is modified so that the gradients during back propagation are not calculated, which can effectively avoid the occurrence of overfitting and improve training efficiency [59]. Finally, the original 16 outputs were changed into two outputs, that is, the original 16 classifications were changed into two classifications: cattle body point cloud and other point clouds.…”

Section: Methodsmentioning

confidence: 99%

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Huang

Guo

Rao

et al. 2019

Sensors

View full text Add to dashboard Cite

For the time-consuming and stressful body measuring task of Qinchuan cattle and farmers, the demand for the automatic measurement of body dimensions has become more and more urgent. It is necessary to explore automatic measurements with deep learning to improve breeding efficiency and promote the development of industry. In this paper, a novel approach to measuring the body dimensions of live Qinchuan cattle with on transfer learning is proposed. Deep learning of the Kd-network was trained with classical three-dimensional (3D) point cloud datasets (PCD) of the ShapeNet datasets. After a series of processes of PCD sensed by the light detection and ranging (LiDAR) sensor, the cattle silhouettes could be extracted, which after augmentation could be applied as an input layer to the Kd-network. With the output of a convolutional layer of the trained deep model, the output layer of the deep model could be applied to pre-train the full connection network. The TrAdaBoost algorithm was employed to transfer the pre-trained convolutional layer and full connection of the deep model. To classify and recognize the PCD of the cattle silhouette, the average accuracy rate after training with transfer learning could reach up to 93.6%. On the basis of silhouette extraction, the candidate region of the feature surface shape could be extracted with mean curvature and Gaussian curvature. After the computation of the FPFH (fast point feature histogram) of the surface shape, the center of the feature surface could be recognized and the body dimensions of the cattle could finally be calculated. The experimental results showed that the comprehensive error of body dimensions was close to 2%, which could provide a feasible approach to the non-contact observations of the bodies of large physique livestock without any human intervention.

show abstract

Section: Methodsmentioning

confidence: 99%

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Huang

Guo

Rao

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…We evaluate CoTrans on about 10,000 cars in Shanghai. The result shows that CoTrans can achieve up to 85% detection accuracy without the need of any labeled data, which is competitive to the accuracy of manual labels [16]. Hence, CoTrans can serve as an automatic suspicious ridesharing car detection mechanism for city governors without the need for labeled ridesharing car data.…”

Section: Application 2: Ridesharing Detection For Unlicensed Car Rmentioning

confidence: 97%

“…If we can detect cars suspected to be ridesharing but not licensed on the ridesharing platform, then city governors can take regulation actions more easily in time. Hence, this project aims to find ridesharing cars from a large number of candidate cars based on their trajectories [16]. The difficulty of ridesharing detection is the lack of historical trajectory data of ridesharing cars (i.e., lack of labeled data) because: (1) some cities do not officially allow ridesharing services yet; (2) even in the cities allowing ridesharing, the trajectory data is held by companies (e.g., DiDi and Uber), which is not always accessible to governors.…”

Section: Application 2: Ridesharing Detection For Unlicensed Car Rmentioning

confidence: 99%

“…To address this difficulty, we develop a ridesharing detection mechanism called CoTrans [16], which can detect whether a car is ridesharing by transferring knowledge from taxis (Figure 3 (b)). Taxis share many similar characteristics with ridesharing cars (e.g., driving distance and time) [17], which makes this transfer feasible.…”

Section: Application 2: Ridesharing Detection For Unlicensed Car Rmentioning

confidence: 99%

See 1 more Smart Citation

Smart City Development With Urban Transfer Learning

2018

Self Cite

View full text Add to dashboard Cite

Nowadays, the smart city development levels of different cities are still unbalanced. For a large number of cities which just started development, the governments will face a critical cold-start problem: 'how to develop a new smart city service with limited data?'. To address this problem, transfer learning can be leveraged to accelerate the smart city development, which we term the urban transfer learning paradigm. This article investigates the common process of urban transfer learning, aiming to provide city planners and relevant practitioners with guidelines on how to apply this novel learning paradigm. Our guidelines include common transfer strategies to take, general steps to follow, and case studies in public safety, transportation management, etc. We also summarize a few research opportunities and expect this article can attract more researchers to study urban transfer learning.

show abstract

“…The first is using auxiliary data of the target city to help build the targeted application. Examples include using temperature to infer humidity and vice versa [14], and leveraging the taxi GPS traces to detect ridesharing cars [13]. The second is to find a source city with adequate data to transfer knowledge.…”

Section: Related Workmentioning

confidence: 99%

Cross-City Transfer Learning for Deep Spatio-Temporal Prediction

Wang

Geng

et al. 2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Spatio-temporal prediction is a key type of tasks in urban computing, e.g., traffic flow and air quality. Adequate data is usually a prerequisite, especially when deep learning is adopted. However, the development levels of different cities are unbalanced, and still many cities suffer from data scarcity. To address the problem, we propose a novel cross-city transfer learning method for deep spatiotemporal prediction tasks, called RegionTrans. RegionTrans aims to effectively transfer knowledge from a data-rich source city to a data-scarce target city. More specifically, we first learn an inter-city region matching function to match each target city region to a similar source city region. A neural network is designed to effectively extract region-level representation for spatio-temporal prediction. Finally, an optimization algorithm is proposed to transfer learned features from the source city to the target city with the region matching function. Using citywide crowd flow prediction as a demonstration experiment, we verify the effectiveness of RegionTrans. Results show that RegionTrans can outperform the state-of-theart fine-tuning deep spatio-temporal prediction models by reducing up to 10.7% prediction error. * Equal contribution Preprint. Work in progress.In literature, existing deep learning approaches are often designed to predict citywide phenomenon as a whole [18,19], and thus it is hard to enable region-level knowledge transfer. To this end, rather than adopting the existing deep neural networks for citywide spatio-temporal prediction (e.g. ), we propose a novel deep transfer learning method. First, we design a region matching function to link each target city region to a similar source region based on the short period of service data or correlated auxiliary data if applicable. Then, in our proposed network structure, to catch the spatio-temporal patterns hidden in the service data, ConvLSTM layers [12] are firstly stacked. Afterward, to encode region representation, we newly add a Conv2D layer with 1 × 1 filter, which is the key and fundamental component of our network to make region-level transfer feasible. Finally, the discrepancy between region representations of the inter-city similar regions is minimized during the network parameter learning for the target city, so as to enable region-level cross-city knowledge transfer. With crowd flow prediction as a showcase [18,19], we verify the feasibility and effectiveness of RegionTrans. Briefly, this paper has the following contributions.(i) To the best of our knowledge, this is the first work to study how to facilitate deep spatio-temporal prediction in a data-scarce target city by transferring knowledge from a data-rich source city.(ii) We propose a novel deep transfer learning method RegionTrans for spatio-temporal prediction tasks by region-level cross-city transfer. RegionTrans first computes inter-city region similarities, and then stacks ConvLSTM and Conv2D (1 × 1 filter) layers to extract region-level representations reflecting spatio-temporal pattern...

show abstract

Ridesharing car detection by transfer learning

Cited by 36 publications

References 31 publications

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Smart City Development With Urban Transfer Learning

Cross-City Transfer Learning for Deep Spatio-Temporal Prediction

Contact Info

Product

Resources

About