Deep learning-based perception systems for autonomous driving: A comprehensive survey

A synthetic digital city dataset for robustness and generalisation of depth estimation models

Existing monocular depth estimation driving datasets are limited in the number of images and the diversity of driving conditions. The images of datasets are commonly in a low resolution and the depth maps are sparse. To overcome these limitations, we produce a Synthetic Digital City Dataset (SDCD) which was collected under 6 different weather driving conditions, and 6 common adverse perturbations caused by the data transmission. SDCD provides a total of 930 K high-resolution RGB images and corresponding perfect observed depth maps. The evaluation shows that depth estimation models which are trained on SDCD provide a clearer, smoother, and more precise long-range depth estimation compared to those trained on one of the best-known driving datasets KITTI. Moreover, we provide a benchmark to investigate the performance of depth estimation models in different adverse driving conditions. Instead of collecting data from the real world, we generate the SDCD under severe driving conditions with perfect observed data in the digital world, enhancing depth estimation for autonomous driving.

A survey on neural-symbolic learning systems

In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence. However, they have been found to lack effective reasoning and cognitive ability. On the other hand, symbolic systems exhibit exceptional cognitive intelligence but suffer from poor learning capabilities when compared to neural systems. Recognizing the advantages and disadvantages of both methodologies, an ideal solution emerges: combining neural systems and symbolic systems to create neural-symbolic learning systems that possess powerful perception and cognition. The purpose of this paper is to survey the advancements in neural-symbolic learning systems from four distinct perspectives: challenges, methods, applications, and future directions. By doing so, this research aims to propel this emerging field forward, offering researchers a comprehensive and holistic overview. This overview will not only highlight the current state-of-the-art but also identify promising avenues for future research.

Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis

Artificial intelligence (AI) now enables automated interpretation of medical images. However, AI's potential use for interventional image analysis remains largely untapped. This is because the post hoc analysis of data collected during live procedures has fundamental and practical limitations, including ethical considerations, expense, scalability, data integrity and a lack of ground truth. Here we demonstrate that creating realistic simulated images from human models is a viable alternative and complement to large-scale in situ data collection. We show that training AI image analysis models on realistically synthesized data, combined with contemporary domain generalization techniques, results in machine learning models that on real data perform comparably to models trained on a precisely matched real data training set. We find that our model transfer paradigm for X-ray image analysis, which we refer to as SyntheX, can even outperform real-data-trained models due to the effectiveness of training on a larger dataset. SyntheX provides an opportunity to markedly accelerate the conception, design and evaluation of X-ray-based intelligent systems. In addition, SyntheX provides the opportunity to test novel instrumentation, design complementary surgical approaches, and envision novel techniques that improve outcomes, save time or mitigate human error, free from the ethical and practical considerations of live human data collection.

Weakly perceived object detection based on an improved CenterNet

Nowadays, object detection methods based on deep neural networks have been widely applied in autonomous driving and intelligent robot systems. However, weakly perceived objects with a small size in the complex scenes own too few features to be detected, resulting in the decrease of the detection accuracy. To improve the performance of the detection model in complex scenes, the detector of an improved CenterNet was developed via this work to enhance the feature representation of weakly perceived objects. Specifically, we replace the ResNet50 with ResNext50 as the backbone network to enhance the ability of feature extraction of the model. Then, we append the lateral connection structure and the dilated convolution to improve the feature enhancement layer of the CenterNet, leading to enriched features and enlarged receptive fields for the weakly sensed objects. Finally, we apply the attention mechanism in the detection head of the network to enhance the key information of the weakly perceived objects. To demonstrate the effectiveness, we evaluate the proposed model on the KITTI dataset and COCO dataset. Compared with the original model, the average precision of multiple categories of the improved CenterNet for the vehicles and pedestrians in the KITTI dataset increased by 5.37%, whereas the average precision of weakly perceived pedestrians increased by 9.30%. Moreover, the average precision of small objects (AP_S) of the weakly perceived small objects in the COCO dataset increase 7.4%. Experiments show that the improved CenterNet can significantly improve the average detection precision for weakly perceived objects.