4D mmWave radar sensors are well suited for city scale Intelligent Transportation Systems (ITS) given their long sensing range, weatherproof functionality, simple mechanical design, and low manufacturing cost. In this paper, we investigate radar-based ITS for scalable traffic analysis. Localization of these radar sensors in a city scale range is a fundamental task in ITS. For mobile ITS setups it requires more endeavor. To address this task, we propose a self-localization approach that matches two descriptions of "road": the one from the geometry of the motion trajectories of cumulatively observed vehicles, and the other one from the aerial laser scan. An ICP (iterative closest point) algorithm is used to register the motion trajectory into the road section of the laser scan to estimate the sensor pose. We evaluates the results and show that it outperforms other map-based radar localization methods, especially for the orientation estimation. Beyond the localization result, we project radar sensor data onto city scale laser scan and generate an scalable occupancy heat map as a traffic analysis tool. This is demonstrated using two radar sensors monitoring an urban area in the real world.
Both visual and auditory information are valuable to determine the salient regions in videos. Deep convolution neural networks (CNN) showcase strong capacity in coping with the audio-visual saliency prediction task. Due to various factors such as shooting scenes and weather, there often exists moderate distribution discrepancy between source training data and target testing data. The domain discrepancy induces to performance degradation on target testing data for CNN models. This paper makes an early attempt to tackle the unsupervised domain adaptation problem for audio-visual saliency prediction. We propose a dual domain-adversarial learning algorithm to mitigate the domain discrepancy between source and target data. First, a specific domain discrimination branch is built up for aligning the auditory feature distributions. Then, those auditory features are fused into the visual features through a cross-modal self-attention module. The other domain discrimination branch is devised to reduce the domain discrepancy of visual features and audio-visual correlations implied by the fused audio-visual features. Experiments on public benchmarks demonstrate that our method can relieve the performance degradation caused by domain discrepancy.
The great success of deep learning is mainly due to the large-scale network architecture and the high-quality training data. However, it is still challenging to deploy recent deep models on portable devices with limited memory and imaging ability. Some existing works have engaged to compress the model via knowledge distillation. Unfortunately, these methods cannot deal with images with reduced image quality, such as the low-resolution (LR) images. To this end, we make a pioneering effort to distill helpful knowledge from a heavy network model learned from high-resolution (HR) images to a compact network model that will handle LR images, thus advancing the current knowledge distillation technique with the novel pixel distillation. To achieve this goal, we propose a Teacher-Assistant-Student (TAS) framework, which disentangles knowledge distillation into the model compression stage and the high resolution representation transfer stage. By equipping a novel Feature Super Resolution (FSR) module, our approach can learn lightweight network model that can achieve similar accuracy as the heavy teacher model but with much fewer parameters, faster inference speed, and lower-resolution inputs. Comprehensive experiments on three widely-used benchmarks, \ie, CUB-200-2011, PASCAL VOC 2007, and ImageNetSub, demonstrate the effectiveness of our approach.