To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.

https://www.mdpi.com/1424-8220/18/12/4308/pdf

A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3.

Recent years have seen rapid deployment of mobile computing and Internet of Things (IoT) networks, which can be mostly attributed to the increasing communication and sensing capabilities of wireless systems. Big data analysis, pervasive computing, and eventually artificial intelligence (AI) are envisaged to be deployed on top of the IoT and create a new world featured by data-driven AI. In this context, a novel paradigm of merging AI and wireless communications, called Wireless AI that pushes AI frontiers to the network edge, is widely regarded as a key enabler for future intelligent network evolution. To this end, we present a comprehensive survey of the latest studies in wireless AI from the data-driven perspective. Specifically, we first propose a novel Wireless AI architecture that covers five key data-driven AI themes in wireless networks, including Sensing AI, Network Device AI, Access AI, User Device AI and Data-provenance AI. Then, for each data-driven AI theme, we present an overview on the use of AI approaches to solve the emerging data-related problems and show how AI can empower wireless network functionalities. Particularly, compared to the other related survey papers, we provide an in-depth discussion on the Wireless AI applications in various data-driven domains wherein AI proves extremely useful for wireless network design and optimization. Finally, research challenges and future visions are also discussed to spur further research in this promising area.

Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective

Collaborative intelligence is a new paradigm for efficient deployment of deep neural networks across the mobile-cloud infrastructure. By dividing the network between the mobile and the cloud, it is possible to distribute the computational workload such that the overall energy and/or latency of the system is minimized. However, this necessitates sending deep feature data from the mobile to the cloud in order to perform inference. In this work, we examine the differences between the deep feature data and natural image data, and propose a simple and effective near-lossless deep feature compressor. The proposed method achieves up to 5% bit rate reduction compared to HEVC-Intra and even more against other popular image codecs. Finally, we suggest an approach for reconstructing the input image from compressed deep features that could serve to supplement the inference performed by the deep model.

Near-Lossless Deep Feature Compression for Collaborative Intelligence

Human lives are important. The decision to allow self-driving vehicles operate on our roads carries great weight. This has been a hot topic of debate between policy-makers, technologists and public safety institutions. The recent Uber Inc. self-driving car crash, resulting in the death of a pedestrian, has strengthened the argument that autonomous vehicle technology is still not ready for deployment on public roads. In this work, we analyze the Uber car crash and shed light on the question, "Could the Uber Car Crash have been avoided?". We apply state-of-the-art Computer Vision models to this highly practical scenario. More generally, our experimental results are an evaluation of various image enhancement and object recognition techniques for enabling pedestrian safety in low-lighting conditions using the Uber crash as a case study.

Enabling Pedestrian Safety using Computer Vision Techniques: A Case Study of the 2018 Uber Inc. Self-driving Car Crash

A promising way to deploy Artificial Intelligence (AI)-based services on mobile devices is to run a part of the AI model (a deep neural network) on the mobile itself, and the rest in the cloud. This is sometimes referred to as collaborative intelligence. In this framework, intermediate features from the deep network need to be transmitted to the cloud for further processing. We study the case where such features are used for multiple purposes in the cloud (multi-tasking) and where they need to be compressible in order to allow efficient transmission to the cloud. To this end, we introduce a new loss function that encourages feature compressibility while improving system performance on multiple tasks. Experimental results show that with the compression-friendly loss, one can achieve around 20% bitrate reduction without sacrificing the performance on several vision-related tasks.

Multi-Task Learning with Compressible Features for Collaborative Intelligence

Object tracking is the cornerstone of many visual analytics systems. While considerable progress has been made in this area in recent years, robust, efficient, and accurate tracking in real-world video remains a challenge. In this paper, we present a hybrid tracker that leverages motion information from the compressed video stream and a general-purpose semantic object detector acting on decoded frames to construct a fast and efficient tracking engine. The proposed approach is compared with several well-known recent trackers on the OTB tracking dataset. The results indicate advantages of the proposed method in terms of speed and/or accuracy. Other desirable features of the proposed method are its simplicity and deployment efficiency, which stems from the fact that it reuses the resources and information that may already exist in the system for other reasons.

MV-YOLO: Motion Vector-Aided Tracking by Semantic Object Detection

Recent studies have shown that collaborative intelligence (CI) is a promising framework for deployment of Artificial Intelligence (AI)-based services on mobile devices. In CI, a deep neural network is split between the mobile device and the cloud. Deep features obtained at the mobile are compressed and transferred to the cloud to complete the inference. So far, the methods in the literature focused on transferring a single deep feature tensor from the mobile to the cloud. Such methods are not applicable to some recent, high-performance networks with multiple branches and skip connections. In this paper, we propose the first bit allocation method for multi-stream, multi-task CI. We first establish a model for the joint distortion of the multiple tasks as a function of the bit rates assigned to different deep feature tensors. Then, using the proposed model, we solve the rate-distortion optimization problem under a total rate constraint to obtain the best rate allocation among the tensors to be transferred. Experimental results illustrate the efficacy of the proposed scheme compared to several alternative bit allocation methods.

Bit Allocation for Multi-Task Collaborative Intelligence

In recent studies, collaborative intelligence (CI) has emerged as a promising framework for deployment of Artificial Intelligence (AI)-based services on mobile/edge devices. In CI, the AI model (a deep neural network) is split between the edge and the cloud, and intermediate features are sent from the edge sub-model to the cloud sub-model. In this paper, we study bit allocation for feature coding in multi-stream CI systems. We model task distortion as a function of rate using convex surfaces similar to those found in distortion-rate theory. Using such models, we are able to provide closed-form bit allocation solutions for single-task systems and scalarized multi-task systems. Moreover, we provide analytical characterization of the full Pareto set for 2-stream k-task systems, and bounds on the Pareto set for 3-stream 2-task systems. Analytical results are examined on a variety of DNN models from the literature to demonstrate wide applicability of the results

Pareto-Optimal Bit Allocation for Collaborative Intelligence.

Collaborative intelligence is a deployment paradigm for deep AI models where some of the layers run on the mobile terminal or network edge, while others run in the cloud. In this scenario, features computed in the model need to be transferred between the edge and the cloud over an imperfect channel. Here we present a simulator to help study the effects of imperfect packet-based transmission of deep features. Our simulator is implemented in Keras and allows users to study the effects of both lossy packet transmission and quantization on the accuracy.

http://summit.sfu.ca/system/files/iritems1/18101/main.pdf

Saeed Ranjbar Alvar

Papers

Multi-Task Learning with Compressible Features for Collaborative Intelligence

MV-YOLO: Motion Vector-Aided Tracking by Semantic Object Detection

Bit Allocation for Multi-Task Collaborative Intelligence

Pareto-Optimal Bit Allocation for Collaborative Intelligence.

DFTS: Deep Feature Transmission Simulator