Video coding algorithms encode and decode an entire video frame while feature coding techniques only preserve and communicate the most critical information needed for a given application. This is because video coding targets human perception, while feature coding aims for machine vision tasks. Recently, attempts are being made to bridge the gap between these two domains. In this work, we propose a video coding framework by leveraging on to the commonality that exists between human vision and machine vision applications using cuboids. This is because cuboids, estimated rectangular regions over a video frame, are computationally efficient, has a compact representation and object centric. Such properties are already shown to add value to traditional video coding systems. Herein cuboidal feature descriptors are extracted from the current frame and then employed for accomplishing a machine vision task in the form of object detection. Experimental results show that a trained classifier yields superior average precision when equipped with cuboidal features oriented representation of the current test frame. Additionally, this representation costs $7\%$ less in bit rate if the captured frames are need be communicated to a receiver.
翻译:视频编码算法编码和解码整个视频框架,而功能编码技术只保存和传递特定应用程序所需的最关键信息。 这是因为视频编码是针对人类感知的, 而功能编码是机器视觉任务的目的。 最近, 正在尝试弥合这两个领域之间的差距。 在这项工作中, 我们提议一个视频编码框架, 利用人类视觉与机器视觉应用之间的共性, 使用幼崽。 这是因为幼崽、 视频框架中估计的矩形区域, 具有计算效率, 具有紧凑的表示法和对象中心。 这些特性已经显示为传统视频编码系统增添价值。 正在从当前框架中提取的 cubotal 特征描述符, 然后用于完成物体探测形式的机器视觉任务。 实验结果显示, 受过训练的叙级者在配有当前测试框架的cubodal 特征时, 能产生更高的平均精确度。 此外, 如果需要将捕获的框传递给接收者, 则这种表示法将降低位速 $$ 7 ⁇ 。