Urban vehicle emission prediction can help the regulation of vehicle pollution and traffic control. However, it is hard to predict the spatiotemporal variation of vehicle emission because of the spatial interactions and temporal correlations between different road segments as well as the high nonlinearity and complexity of vehicle emission variation. The existing methods solve the problem by splitting the region into standard segments or grids based on conventional deep learning methods, without considering that urban vehicle emission varies by graph-structured traffic road network and depends on many complex external environment factors. To address these issues, a spatiotemporal graph convolution multifusion network (ST-MFGCN) is proposed to leverage the graph structural properties as the inherent connectivity of road network for urban vehicle emission prediction, which can capture the vehicle emission spatiotemporal variation patterns and learn the effects of complex environmental factors. The proposed model consists of three parts: 1) a spatiotemporal graph convolution module to capture spatiotemporal dependencies by merging closeness, period, and trend sequences with temporal convolution as well as graph convolution is introduced to model the spatial dependencies; 2) an external factor component to divide multisource external factors into global and individual external features; and 3) a general fusion component to merge the spatiotemporal patterns and the external features as well as fit the mutation of emission measurement data by multifusion strategy. Finally, the proposed model is evaluated on the practical monitoring data of vehicle emission data in Hefei, and the results demonstrate that our proposed model can predict regional vehicle emissions effectively.

Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields. Event cameras are more sensitive to junction leakage current and photocurrent as they output differential signals, losing the smoothing function of the integral imaging process in the RGB camera. The logarithmic conversion further amplifies noise, especially in low-contrast conditions. Recently, researchers proposed a series of datasets and evaluation metrics but limitations remain: 1) the existing datasets are small in scale and insufficient in noise diversity, which cannot reflect the authentic working environments of event cameras; and 2) the existing denoising evaluation metrics are mostly referenced evaluation metrics, relying on APS information or manual annotation. To address the above issues, we construct a large-scale event denoising dataset (multilevel benchmark for event denoising, E-MLB) for the first time, which consists of 100 scenes, each with four noise levels, that is 12 times larger than the largest existing denoising dataset. We also propose the first nonreference event denoising metric, the event structural ratio (ESR), which measures the structural intensity of given events. ESR is inspired by the contrast metric, but is independent of the number of events and projection direction. Based on the proposed benchmark and ESR, we evaluate the most representative denoising algorithms, including classic and SOTA, and provide denoising baselines under various scenes and noise levels. The corresponding results and codes are available at https://github.com/KugaMaxx/cuke-emlb

Helicopters are complex high-order and time-varying nonlinear systems, strongly coupling with aerodynamic forces, engine dynamics, and other phenomena. Therefore, it is a great challenge to investigate system identification for dynamic modeling and adaptive control for helicopters. In this paper, we address the system identification problem as dynamic regression and propose to represent the uncertainties and the hidden states in the system dynamic model with a deep convolutional neural network. Particularly, the parameters of the network are directly learned from the real flight data of aerobatic helicopter. Since the deep convolutional model has a good performance for describing the dynamic behavior of the hidden states and uncertainties in the flight process, the proposed identifier manifests strong robustness and high accuracy, even for untrained aerobatic maneuvers. The effectiveness of the proposed method is verified by various experiments with the real-world flight data from the Stanford Autonomous Helicopter Project. Consequently, an adaptive flight control scheme including a deep convolutional identifier and a backstepping-based controller is presented. The stability of the flight control scheme is rigorously proved by the Lyapunov theory. It reveals that the tracking errors for both the position and attitude of unmanned helicopter asymptotic converge to a small neighborhood of the origin.

Rapid progress on disaster detection and assessment has been achieved with the development of deep-learning techniques and the wide applications of remote sensing images. However, it is still a great challenge to train an accurate and robust disaster detection network due to the class imbalance of existing data sets and the lack of training data. This paper aims at synthesizing disaster remote sensing images with multiple disaster types and different building damage with generative adversarial networks (GANs), making up for the shortcomings of the existing data sets. However, existing models are inefficient in multi-disaster image translation due to the diversity of disaster and inevitably change building-irrelevant regions caused by directly operating on the whole image. Thus, we propose two models: disaster translation GAN can generate disaster images for multiple disaster types using only a single model, which uses an attribute to represent disaster types and a reconstruction process to further ensure the effect of the generator; damaged building generation GAN is a mask-guided image generation model, which can only alter the attribute-specific region while keeping the attribute-irrelevant region unchanged. Qualitative and quantitative experiments demonstrate the validity of the proposed methods. Further experimental results on the damaged building assessment model show the effectiveness of the proposed models and the superiority compared with other data augmentation methods.