Related papers: A System-Level Solution for Low-Power Object Detec…
In this paper, we present Mondrian, an edge system that enables high-performance object detection on high-resolution video streams. Many lightweight models and system optimization techniques have been proposed for resource-constrained…
Object detection is a cornerstone of environmental perception in advanced driver assistance systems(ADAS). However, most existing methods rely on RGB cameras, which suffer from significant performance degradation under low-light conditions…
Memory bandwidth has become the real-time bottleneck of current deep learning accelerators (DLA), particularly for high definition (HD) object detection. Under resource constraints, this paper proposes a low memory traffic DLA chip with…
Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual…
We propose a domain adaptation approach for object detection. We introduce a two-step method: the first step makes the detector robust to low-level differences and the second step adapts the classifiers to changes in the high-level…
Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary to sacrifice accuracy to ensure the infer speed of the…
This paper proposes a novel approach to create an automated visual surveillance system which is very efficient in detecting and tracking moving objects in a video captured by moving camera without any apriori information about the captured…
Fast and accurate video object recognition, which relies on frame-by-frame video analytics, remains a challenge for resource-constrained devices such as traffic cameras. Recent advances in mobile edge computing have made it possible to…
Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and…
We consider the problem of detecting objects, as they come into view, from videos in an online fashion. We provide the first real-time solution that is guaranteed to minimize the delay, i.e., the time between when the object comes in view…
We present a highly compact run-time monitoring approach for deep computer vision networks that extracts selected knowledge from only a few (down to merely two) hidden layers, yet can efficiently detect silent data corruption originating…
The Internet of Things (IoT) and smart city paradigm includes ubiquitous technology to extract context information in order to return useful services to users and citizens. An essential role in this scenario is often played by computer…
The retail sector presents several open and challenging problems that could benefit from advanced pattern recognition and computer vision techniques. One such critical challenge is planogram compliance control. In this study, we propose a…
Object detection aims at high speed and accuracy simultaneously. However, fast models are usually less accurate, while accurate models cannot satisfy our need for speed. A fast model can be 10 times faster but 50\% less accurate than an…
Object Detection is the task of classification and localization of objects in an image or video. It has gained prominence in recent years due to its widespread applications. This article surveys recent developments in deep learning based…
Object detection and classification are crucial tasks across various application domains, particularly in the development of safe and reliable Advanced Driver Assistance Systems (ADAS). Existing deep learning-based methods such as…
Early object detection (OD) is a crucial task for the safety of many dynamic systems. Current OD algorithms have limited success for small objects at a long distance. To improve the accuracy and efficiency of such a task, we propose a novel…
Object detection in images has reached unprecedented performances. The state-of-the-art methods rely on deep architectures that extract salient features and predict bounding boxes enclosing the objects of interest. These methods essentially…
Training CNN for detection is time-consuming due to the large dataset and complex network modules, making it hard to search architectures on detection datasets directly, which usually requires vast search costs (usually tens and even…
We describe an approach for segmenting an image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appearance and motion statistics into a cost functional, that is seeded…