Over the past decade, several approaches have been proposed to learn disentangled representations for video prediction. However, reported experiments are mostly based on standard benchmark datasets such as Moving MNIST and Bouncing Balls. In this work, we address the problem of learning disentangled representation for video prediction in an industrial environment. To this end, we use decompositional disentangled variational autoencoder, a deep generative model that aims to decompose and recognize overlapped boxes on a pallet. Specifically, this approach disentangles each frame into a dynamic component (box appearance) and a temporally variant component (box location). We evaluate this approach on a new dataset, which contains 40000 video sequences. The experimental results demonstrate the ability to learn both the decomposition of the bounding boxes and their reconstruction without explicit supervision.

This paper presents the results of research and fabrication of a colour laser marking device on metal surfaces using a high-power fiber laser with a MOPA (Master oscillator power amplifier) configuration by intergrating semi-finished modules. Using our manufactured colour laser marking device, the effects of laser parameters such as laser power, laser pulse repetition frequency, beam scanning speed, line width on forming colour process have been researched and evaluated explicitly to provide the optimal set of parameters for the colours on each specific stainless steel and titanium metal.