随着世界中面临的潜在安全威胁变得越来越多，企业对部署复杂的监控系统的需求开始不断增长。能够作为一个直观的“机器人眼睛”，准确实时地检测无人看管行李的智能系统，已经成为机场、火车站、商场和其他公共区域的安保人员的关键需求。本文介绍了用于火车站的无人看管行李检测的 Microsoft Common Objects in Context (MS-COCO) 检测模式。
传统的检测方法涉及使用块式方向直方图（SIFT 或 HOG）功能，这无法在标准数据集中实现高精度，如 PASCAL VOC。这些方法会编码物体的低级别特性，因此无法有效区分不同的标签。基于深度学习（卷积网络）的方法成为图像物体检测的领先方法。各种网络拓扑已经随着时间的变化进行了演进，如图 1 所示。
SoftLab-NSK develops complete TV broadcast automation solutions that work with the 4K format and HEVC compression and include functionality for video encoding. When the company wanted to expand its ﬂagship Forward T* line of playout servers, it needed the most efficient solution for video transcoding.
This blog post is part of a series that describes my summer school project at CERN openlab. In the first post we introduced the problem of track reconstruction and the track seeds filtering. Today we are going to discuss the model architecture and the results.
In a world becoming ever more attuned to potential security threats, the need to deploy sophisticated surveillance systems is increasing. An intellectual system that functions as an intuitive “robotic eye” for accurate, real-time detection of unattended baggage has become a critical need for security personnel at airports, stations, malls, and in other public areas. This article discusses inferencing a Microsoft Common Objects in Context (MS-COCO) detection model for detecting unattended baggage in a train station.
Machine learning applications are very compute intensive by their nature. That is why optimization for performance is quite important for them. One of the most popular libraries, Tensorflow*, already has an embedded timeline feature that helps understand which parts of the computational graph are causing bottlenecks but it lacks some advanced features like an architectural analysis.