Roadside vision-based 3D object detection is vital in many applications, such as autonomous driving. The mainstream methods enhance the accuracy of distance estimation by converting predicted height distribution into depth distribution. However, predicting object’s height in roadside perception is challenging, particularly for distant and small objects. Therefore, this work proposes a series of methods to optimize height prediction. Firstly, we propose depth and height decoding supervision methods to optimize the height network by supervising the decoded depth and height values. Then, a height distribution alignment loss is introduced to optimize the height network by constraining the consistency of height distributions among objects of the same category. Experimental results demonstrate that the proposed optimization methods can effectively improve the accuracy of roadside vision-based 3D object detection. For instance, our methods improve the accuracies by 2.31%, 4.33%, and 4.24% for the cyclist category at easy, medium, and hard levels, respectively.

Reinforcement Learning (RL) over motion skill space has been verified to generate more diverse behaviors than that over low-level control space, and has exhibited superior autonomous driving performance in complex traffic scenarios. However, the incomplete observations pose challenges in achieving efficient skill exploration under unsupervised conditions, hampering the driving performance and applicability. In this paper, we propose a dynamic-aware RL with hybrid network (Da-HnRL) to develop a pseudo-hierarchical planning framework for better motion skill learning in challenging dense traffics. Based on the semi-POMDP modeling, we construct a hybrid network with skip connections as the RL backbone, facilitating a better understanding of the underlying system dynamics. Then we design an efficiency-oriented reward shaping mechanism to incentivize active skill exploration, promoting enhanced trade-off between exploration and exploitation. Furthermore, we provide a comprehensive scoring mechanism for policy identification, ensuring the near-optimality. We validate the proposed methods on challenging dense-traffic tasks. The results demonstrate the superiority of our approach over previous methods, with improved learning efficiency, driving stability and generalization.

The state-of-the-art deep neural networks have made a great breakthrough in remote sensing image classification. However, the heavy dependence on large-scale data sets limits the application of the deep learning to synthetic aperture radar (SAR) automatic target recognition (ATR) field where the target sample set is generally small. In this work, a metalearning framework named MSAR, consisting of a metalearner and a base-learner, is proposed to solve the sample restriction problem, which can learn a good initialization as well as a proper update strategy. After training, MSAR can implement fast adaptation with a few training images on new tasks. To the best of our knowledge, this is the first study to solve a few-shot SAR target classification via metalearning. In particular, the few-task problem is defined by analyzing the effect of available training classes on the performance of metalearning models. In order to reduce the metalearning difficulties caused by the few-task problem, three transfer-learning methods are employed, which can leverage the prior knowledge from the pretraining phase. Besides, we design a hard task mining method for effective metalearning. Based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set, a specialized data set named NIST-SAR is devised to train and evaluate the proposed method. The experiments on NIST-SAR have shown that the proposed method yields better performances with the largest absolute improvements of 1.7% and 2.3% for 1-shot and 5-shot, respectively, over the next best, which indicates that the proposed method is promising and metalearning is a feasible solution for few-shot SAR ATR.

Feature pyramid is the mainstream method for multi-scale object detection. In most detectors with feature pyramid, each proposal is predicted based on feature grids pooled from only one feature level, which is assigned heuristically. Recent studies report that the feature representation extracted using this method is sub-optimal, since they ignore the valid information exists on other unselected layers of the feature pyramid. To address this issue, researchers present to fuse valid information across all feature levels. However, these methods can be further improved: the feature fusion strategies, which use common operation (element-wise max or sum) in most detectors, should be replaced by a more flexible way. In this work, a novel method called feature adaptive selection subnetwork (FAS-Net) is proposed to construct effective features for detecting objects of different scales. Particularly, its adaption consists of two level: global attention and local adaptive selection. First, we model the global context of each feature map with global attention based feature selection module (GAFSM), which can strengthen the effective features across each layer adaptively. Then we extract the features of each region of interest (RoI) on the entire feature pyramid to construct a RoI feature pyramid. Finally, the RoI feature pyramid is sent to the feature adaptive selection module (FASM) to integrate the strengthened features according to the input adaptively. Our FAS-Net can be easily extended to other two-stage object detectors with feature pyramid, and supports to analyze the importance of different feature levels for multi-scale objects quantitatively. Besides, FAS-Net can also be further applied to instance segmentation task and get consistent improvements. Experiments on PASCAL07/12 and MSCOCO17 demonstrate the effectiveness and generalization of the proposed method.

Object detection has been a building block in computer vision. Though considerable progress has been made, there still exist challenges for objects with small size, arbitrary direction, and dense distribution. Apart from natural images, such issues are especially pronounced for aerial images of great importance. This paper presents a novel multi-category rotation detector for small, cluttered and rotated objects, namely SCRDet. Specifically, a sampling fusion network is devised which fuses multi-layer feature with effective anchor sampling, to improve the sensitivity to small objects. Meanwhile, the supervised pixel attention network and the channel attention network are jointly explored for small and cluttered object detection by suppressing the noise and highlighting the objects feature. For more accurate rotation estimation, the IoU constant factor is added to the smooth L1 loss to address the boundary problem for the rotating bounding box. Extensive experiments on two remote sensing public datasets DOTA, NWPU VHR-10 as well as natural image datasets COCO, VOC2007 and scene text data ICDAR2015 show the state-of-the-art performance of our detector. The code and models will be available at https://github.com/DetectionTeamUCAS.

Deep learning based object detection has achieved great success. However, these supervised learning methods are data-hungry and time-consuming. This restriction makes them unsuitable for limited data and urgent tasks, especially in the applications of remote sensing. Inspired by the ability of humans to quickly learn new visual concepts from very few examples, we propose a training-free, one-shot geospatial object detection framework for remote sensing images. It consists of (1) a feature extractor with remote sensing domain knowledge, (2) a multi-level feature fusion method, (3) a novel similarity metric method, and (4) a 2-stage object detection pipeline. Experiments on sewage treatment plant and airport detections show that proposed method has achieved a certain effect. Our method can serve as a baseline for training-free, one-shot geospatial object detection.