Real-time object detection is critical for the decision-making process for many real-world applications, such as collision avoidance and path planning in autonomous driving. This work presents an innovative real-time streaming perception method, Transtreaming, which addresses the challenge of real-time object detection with dynamic computational delay. The core innovation of Transtreaming lies in its adaptive delay-aware transformer, which can concurrently predict multiple future frames and select the output that best matches the real-world present time, compensating for any system-induced computation delays. The proposed model outperforms the existing state-of-the-art methods, even in single-frame detection scenarios, by leveraging a transformer-based methodology. It demonstrates robust performance across a range of devices, from powerful V100 to modest 2080Ti, achieving the highest level of perceptual accuracy on all platforms. Unlike most state-of-the-art methods that struggle to complete computation within a single frame on less powerful devices, Transtreaming meets the stringent real-time processing requirements on all kinds of devices. The experimental results emphasize the system's adaptability and its potential to significantly improve the safety and reliability for many real-world systems, such as autonomous driving.
Nowadays, plenty of deep learning technologies are being applied to all aspects of autonomous driving with promising results. Among them, object detection is the key to improve the ability of an autonomous agent to perceive its environment so that it can (re)act. However, previous vision-based object detectors cannot achieve satisfactory performance under real-time driving scenarios. To remedy this, we present the real-time steaming perception system in this paper, which is also the 2nd Place solution of Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021) for the detec…
University of California, Berkeley（加州大学伯克利分校）；Google Research（谷歌研究院）；Microsoft Research（微软研究院）；Amazon（亚马逊）
Efficient vision works maximize accuracy under a latency budget. These works evaluate accuracy offline, one image at a time. However, real-time vision applications like autonomous driving operate in streaming settings, where ground truth changes between inference start and finish. This results in a significant accuracy drop. Therefore, a recent work proposed to maximize accuracy in streaming settings on average. In this paper, we propose to maximize streaming accuracy for every environment context. We posit that scenario difficulty influences the initial (offline) accuracy difference, while ob…
Streaming perception is a critical task in autonomous driving that requires balancing the latency and accuracy of the autopilot system. However, current methods for streaming perception are limited as they only rely on the current and adjacent two frames to learn movement patterns. This restricts their ability to model complex scenes, often resulting in poor detection results. To address this limitation, we propose LongShortNet, a novel dual-path network that captures long-term temporal motion and integrates it with short-term spatial semantics for real-time perception. LongShortNet is notable…
Recognizing the surrounding environment at low latency is critical in autonomous driving. In real-time environment, surrounding environment changes when processing is over. Current detection models are incapable of dealing with changes in the environment that occur after processing. Streaming perception is proposed to assess the latency and accuracy of real-time video perception. However, additional problems arise in real-world applications due to limited hardware resources, high temperatures, and other factors. In this study, we develop a model that can reflect processing delays in real time …
In this report, we introduce our real-time 2D object detection system for the realistic autonomous driving scenario. Our detector is built on a newly designed YOLO model, called YOLOX. On the Argoverse-HD dataset, our system achieves 41.0 streaming AP, which surpassed second place by 7.8/6.1 on detection-only track/fully track, respectively. Moreover, equipped with TensorRT, our model achieves the 30FPS inference speed with a high-resolution input size (e.g., 1440-2304). Code and models will be available at https://github.com/Megvii-BaseDetection/YOLOX
DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception
Institute of Artificial Intelligence, Southwest Jiaotong University（西南交通大学人工智能研究院）；School of Engineering and Technology, University of Washington（华盛顿大学工程与技术学院）；Institute for Intelligent Computing, Alibaba Group（阿里巴巴集团智能计算研究所）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）
MTD: Multi-Timestep Detector for Delayed Streaming Perception
School of Computer and Electronic Information, Guangxi University（广西大学计算机与电子信息学院）；Guangxi Intelligent Digital Services Research Center of Engineering Technology（广西智能数字服务工程技术研究中心）
StreamMOS: Streaming Moving Object Segmentation with Multi-View Perception and Dual-Span Memory
Faculty of Robot Science and Engineering, Northeastern University（东北大学机器人科学与工程学院）；National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University（东北大学工业智能与系统优化国家前沿科学中心）；Key Laboratory of Data Analytics and Optimization for Smart Industry, Ministry of Education, Northeastern University（东北大学智慧工业数据分析与优化教育部重点实验室）
Huazhong University of Science and Technology（华中科技大学）；Megvii Technology（旷视科技）
Autonomous driving requires the model to perceive the environment and (re)act within a low latency for safety. While past works ignore the inevitable changes in the environment after processing, streaming perception is proposed to jointly evaluate the latency and accuracy into a single metric for video online perception. In this paper, instead of searching trade-offs between accuracy and speed like previous works, we point out that endowing real-time models with the ability to predict the future is the key to dealing with this problem. We build a simple and effective framework for streaming pe…
In recent years, vision-centric perception has flourished in various autonomous driving tasks, including 3D detection, semantic map construction, motion forecasting, and depth estimation. Nevertheless, the latency of vision-centric approaches is too high for practical deployment (e.g., most camera-based 3D detectors have a runtime greater than 300ms). To bridge the gap between ideal research and real-world applications, it is necessary to quantify the trade-off between performance and efficiency. Traditionally, autonomous-driving perception benchmarks perform the offline evaluation, neglecting…
Huazhong University of Science and Technology（华中科技大学）；Megvii Technology（旷视科技）
The perceptive models of autonomous driving require fast inference within a low latency for safety. While existing works ignore the inevitable environmental changes after processing, streaming perception jointly evaluates the latency and accuracy into a single metric for video online perception, guiding the previous works to search trade-offs between accuracy and speed. In this paper, we explore the performance of real time models on this metric and endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. Specifically, we build …
Embodied perception refers to the ability of an autonomous agent to perceive its environment so that it can (re)act. The responsiveness of the agent is largely governed by latency of its processing pipeline. While past work has studied the algorithmic trade-off between latency and accuracy, there has not been a clear metric to compare different methods along the Pareto optimal latency-accuracy curve. We point out a discrepancy between standard offline evaluation and real-time applications: by the time an algorithm finishes processing a particular frame, the surrounding world has changed. To th…
Modern autonomous vehicles rely heavily on mechanical LiDARs for perception. Current perception methods generally require 360° point clouds, collected sequentially as the LiDAR scans the azimuth and acquires consecutive wedge-shaped slices. The acquisition latency of a full scan (~ 100ms) may lead to outdated perception which is detrimental to safe operation. Recent streaming perception works proposed directly processing LiDAR slices and compensating for the narrow field of view (FOV) of a slice by reusing features from preceding slices. These works, however, are all based on a single modality…
Perception of the lane boundaries is crucial for the tasks related to autonomous trajectory control. In this paper, several methodologies for lane detection are discussed with an experimental illustration: Hough transformation, Blob analysis, and Bird's eye view. Following the abstraction of lane marks from the boundary, the next approach is applying a control law based on the perception to control steering and speed control. In the following, a comparative analysis is made between an open-loop response, PID control, and a neural network control law through graphical statistics. To get the per…
SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding
Xiamen University（厦门大学）；Beijing Institute of Technology（北京理工大学）；Fudan University（复旦大学）；Shanghai Jiao Tong University（上海交通大学）；University of Hong Kong（香港大学）；China Telecom（中国电信）
StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；Nanjing University（南京大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）
