摘要 :
With the latest advances in image sensor technology, cameras are able to generate video with tens of megapixels per frame. These high resolution videos streams offer great potential to be used in the surveillance domain. For groun...
展开
With the latest advances in image sensor technology, cameras are able to generate video with tens of megapixels per frame. These high resolution videos streams offer great potential to be used in the surveillance domain. For ground based systems, gigapixel streams are already used with great effect as illustrated by the ICME 2019 crowd counting challenge. However, for Unmanned Aerial Vehicles (UAVs), this vast stream of data exceeds the limit of transmission bandwidth to send this data back to the ground. On board data analysis and selection is thus required to use and benefit from high resolution cameras. This paper presents a result of the CAVIAR project, where a combination of hardware and algorithms was designed to answer the question: "how to exploit a high resolution high frame rate camera on board a UAV?'. With the associated size, weight and power limitations, we implement data reduction by deploying deep learning on hardware to find the relevant information and transmit it to an operator station. The proposed solution aims at employing the high resolution potential of the sensor only onto objects of interest. We encode and transmit the identified regions containing those objects of interest (ROI) at the original resolution and framerate, while also transmitting the downscaled background to provide context for an operator. We demonstrate using a 35 fps, 65 Megapixel camera that this set-up indeed saves considerable bandwidth while retaining all important video data at high quality at the same time.
收起
摘要 :
With the latest advances in image sensor technology, cameras are able to generate video with tens of megapixels per frame. These high resolution videos streams offer great potential to be used in the surveillance domain. For groun...
展开
With the latest advances in image sensor technology, cameras are able to generate video with tens of megapixels per frame. These high resolution videos streams offer great potential to be used in the surveillance domain. For ground based systems, gigapixel streams are already used with great effect as illustrated by the ICME 2019 crowd counting challenge. However, for Unmanned Aerial Vehicles (UAVs), this vast stream of data exceeds the limit of transmission bandwidth to send this data back to the ground. On board data analysis and selection is thus required to use and benefit from high resolution cameras. This paper presents a result of the CAVIAR project, where a combination of hardware and algorithms was designed to answer the question: "how to exploit a high resolution high frame rate camera on board a UAV?'. With the associated size, weight and power limitations, we implement data reduction by deploying deep learning on hardware to find the relevant information and transmit it to an operator station. The proposed solution aims at employing the high resolution potential of the sensor only onto objects of interest. We encode and transmit the identified regions containing those objects of interest (ROI) at the original resolution and framerate, while also transmitting the downscaled background to provide context for an operator. We demonstrate using a 35 fps, 65 Megapixel camera that this set-up indeed saves considerable bandwidth while retaining all important video data at high quality at the same time.
收起
摘要 :
The growth in the use of high definition (HD) and above video resolutions streams has outstripped the rate at which network infrastructure has been deployed. Video streaming applications require appropriate rate control techniques...
展开
The growth in the use of high definition (HD) and above video resolutions streams has outstripped the rate at which network infrastructure has been deployed. Video streaming applications require appropriate rate control techniques that make use of the specific characteristics of the video content, such as the regions of interest (ROI). With the introduction of high efficiency video coding (HEVC) streams, we consider new coding features to make a novel ROI-based rate control (RC) algorithm. The proposed approach introduces tiling in a ROI-based rate control scheme. It aims at enhancing the quality of important regions (i.e. faces for a videoconferencing system) considering independently coded regions lying within an ROI and helps evaluating the ROI quality under poor channel conditions. Our work consists of two major steps. First, we designed a RC algorithm based on an independent processing of tiles of different regions. Second, we investigate the effect of ROI- and tile-based rate control algorithm on the decoded quality of the stream transmitted over a lossy channel.
收起
摘要 :
The growth in the use of high definition (HD) and above video resolutions streams has outstripped the rate at which network infrastructure has been deployed. Video streaming applications require appropriate rate control techniques...
展开
The growth in the use of high definition (HD) and above video resolutions streams has outstripped the rate at which network infrastructure has been deployed. Video streaming applications require appropriate rate control techniques that make use of the specific characteristics of the video content, such as the regions of interest (ROI). With the introduction of high efficiency video coding (HEVC) streams, we consider new coding features to make a novel ROI-based rate control (RC) algorithm. The proposed approach introduces tiling in a ROI-based rate control scheme. It aims at enhancing the quality of important regions (i.e. faces for a videoconferencing system) considering independently coded regions lying within an ROI and helps evaluating the ROI quality under poor channel conditions. Our work consists of two major steps. First, we designed a RC algorithm based on an independent processing of tiles of different regions. Second, we investigate the effect of ROI- and tile-based rate control algorithm on the decoded quality of the stream transmitted over a lossy channel.
收起
摘要 :
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essentia...
展开
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essential for synthesizing the view requested by a remote user are included in an ROI, which is compressed and transmitted with high priority. Since the data for the desired view are transmitted with the data for its neighboring views as the ROI, the user can render high quality novel views around the desired viewpoint before the arrival of the next frame data. Thus our method can compensate the movement of the remote user even if the network has high latency. Since the user can arbitrarily choose the movable range of the viewpoint by changing the size and weight ratio of the ROI, we call this functionality view-dependent scalability. Using a modified JPEG2000 codec, we evaluated the view-dependent scalability of our scheme by measuring the quality of synthesized views against the distance from the originally desired viewpoint.
收起
摘要 :
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essentia...
展开
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essential for synthesizing the view requested by a remote user are included in an ROI, which is compressed and transmitted with high priority. Since the data for the desired view are transmitted with the data for its neighboring views as the ROI, the user can render high quality novel views around the desired viewpoint before the arrival of the next frame data. Thus our method can compensate the movement of the remote user even if the network has high latency. Since the user can arbitrarily choose the movable range of the viewpoint by changing the size and weight ratio of the ROI, we call this functionality view-dependent scalability. Using a modified JPEG2000 codec, we evaluated the view-dependent scalability of our scheme by measuring the quality of synthesized views against the distance from the originally desired viewpoint.
收起
摘要 :
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essentia...
展开
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essential for synthesizing the view requested by a remote user are included in an ROI, which is compressed and transmitted with high priority. Since the data for the desired view are transmitted with the data for its neighboring views as the ROI, the user can render high quality novel views around the desired viewpoint before the arrival of the next frame data. Thus our method can compensate the movement of the remote user even if the network has high latency. Since the user can arbitrarily choose the movable range of the viewpoint by changing the size and weight ratio of the ROI, we call this functionality view-dependent scalability. Using a modified JPEG2000 codec, we evaluated the view-dependent scalability of our scheme by measuring the quality of synthesized views against the distance from the originally desired viewpoint.
收起
摘要 :
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essentia...
展开
This paper proposes a scalable coding scheme for interactive streaming of dynamic light fields, in which a region of interest (ROI) approach is applied for multi-view image sets. In our method, the image segments that are essential for synthesizing the view requested by a remote user are included in an ROI, which is compressed and transmitted with high priority. Since the data for the desired view are transmitted with the data for its neighboring views as the ROI, the user can render high quality novel views around the desired viewpoint before the arrival of the next frame data. Thus our method can compensate the movement of the remote user even if the network has high latency. Since the user can arbitrarily choose the movable range of the viewpoint by changing the size and weight ratio of the ROI, we call this functionality view-dependent scalability. Using a modified JPEG2000 codec, we evaluated the view-dependent scalability of our scheme by measuring the quality of synthesized views against the distance from the originally desired viewpoint.
收起
摘要 :
The very heart and soul of a Process Analyzer lies in its ability to return fantastic profits and reliable results when compared to Laboratory Instrumental Analysis. The "Grab 'n' Go" method is all too common even to this day in p...
展开
The very heart and soul of a Process Analyzer lies in its ability to return fantastic profits and reliable results when compared to Laboratory Instrumental Analysis. The "Grab 'n' Go" method is all too common even to this day in process plant operations. An actual example of the profitability of an on-line gas chromatograph is presented from prior published results (1) and a detailed financial analysis is presented based on a proposed process gas chromatograph installation. The laboratory analysis for the required analyte is extremely labor intensive and the analyte is a toxic substance. The process operates around-the-clock and requires data presented in real-time. The laboratory protocol compromises this manufacturing operation. The original Financial Analyses (1992) have been brought to current values by U.S. Department of Labor Consumer Price Indices (2) (1992 AVG to 2005 FIRST HALF where 1982-84=100) and will be used to address these issues from an Asset Management optimization based upon the on-going Laboratory Operation. A case will be made for managing the manufacturing process in the most cost effective manner. Lost profit opportunities will be identified based upon cost of on-going Laboratory Analyses and additional profit opportunities will be identified based upon increases in Manufacturing Efficiency allowed by the timely results from the Process Gas Chromatograph results.
收起
摘要 :
ROI coding can effectively improve the subjective quality of image. There are some known disadvantages in existing ROI coding methods. This paper presents a new ROI coding method based code block selection mechanism. The method is...
展开
ROI coding can effectively improve the subjective quality of image. There are some known disadvantages in existing ROI coding methods. This paper presents a new ROI coding method based code block selection mechanism. The method is to separate ROI and background data, and to place them to individual code blocks, ROI code block and background code block, which are put to entropy encoder independently. In the bit-stream allocation phase, a weight is assigned to the distort-length slope of ROI code block, which is intended to change the order by which the respective code blocks are assembled to stream. To transfer the information of the separated ROI and background, each original code block is duplicated logically in packet header. By assigning the same value as original code block to the number of bit planes of logical code block which has no data actually, the length of tag tree code is reduced. Because the separated code block can be assembled flexibly, the method enables the dynamic stream allocation according to the content of image.
收起
原文获取