KEYWORDS: Video, Video compression, Machine vision, Distortion, Video coding, Signal processing, Image compression, Visual process modeling, Networks, Image processing
We previously trained the compression network via optimization of bit-rate and distortion (feature domain MSE) [1]. In this paper, we propose feature map compression method for video coding for machine (VCM) based on deep learning-based compression network that joint training for optimizing both compressed bit rate and machine vision task performance. We use bmshij2018-hyperporior model in the CompressAI [2] as the compression network, and compress the feature map which is the output of stem layer in the Faster R-CNN X101-FPN network of Detectron2 [3]. We evaluated the proposed method by evaluation framework for MPEG VCM. The proposed method shows the better results than VVC of MPEG VCM anchor.
KEYWORDS: Video, Receivers, 3D video streaming, 3D image processing, 3D displays, Computer programming, Prototyping, 3D image enhancement, Antennas, Multiplexers
This paper presents 8-VSB & M/H hybrid 3DTV system for ATSC terrestrial 3DTV broadcasting services. The system
transmits MPEG-2 encoded left images through HD main channel (8-VSB) and H.264 encoded right images through
mobile channel (M/H) simultaneously. Basically hybrid 3DTV support stereoscopic 3D HD services composed of mixed
quality left/right images for 3D image rendering. For more comfortable 3D service and human factors under hybrid
3DTV service environment, we also propose new video quality enhancement technologies with small amount of
disparity map information. In this paper, we propose 8-VSB & M/H hybrid 3DTV system which enables stereoscopic 3D
HD, 2D HD fixed and 2D mobile broadcasting concurrently within 6MHz bandwidth, and the proposed system will
provide maximum channel flexibility and extended service functionalities as well as fully backward compatibility with
legacy 2D receivers.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.