“…It can be observed from Table 2 that the proposed architecture has a lower gate count than that from [9] and [10] but not [5] and [11]; however, clock cycles required by [5] and [11] are much greater than the proposed one. [10] achieved fewer clock cycles at the cost of using large size memories and higher gate count.…”
Section: Implementation Results Of the Proposed Architecturementioning
confidence: 94%
“…[10] achieved fewer clock cycles at the cost of using large size memories and higher gate count. The resolution used in [5] is 1080p and is four times less than that of all the other architectures. We have achieved a faster architecture in our design than [5] but at the stake of larger gate count.…”
Section: Implementation Results Of the Proposed Architecturementioning
confidence: 99%
“…The resolution used in [5] is 1080p and is four times less than that of all the other architectures. We have achieved a faster architecture in our design than [5] but at the stake of larger gate count. The main reason for the better results of the proposed architecture is the use of small size distributed memories and parallel filtering.…”
Section: Implementation Results Of the Proposed Architecturementioning
confidence: 99%
“…The filtering in HEVC is less complex and more efficient than the deblocking filter of the previous H.264 standard [5]. The DBF in HEVC employs parallel filtering to improve subjective and objective quality by suppressing and removing blocking artifacts [6].…”
This paper proposes the architecture of a deblocking filter (DBF) that removes blocking artifacts in new emerging High Efficiency Video Coding (HEVC). A parallel architecture for both normal and strong filtering modes of HEVC is proposed. Distributed memories and two data paths increase the parallelism and make the architecture more efficient. The proposed architecture is described by Verilog and implemented on FPGA. The architecture can realize real time to compute 4K UHD video at 30 fps by using 46.65 million clocks with total equivalent gate count of 46K. The maximum delay time for output to come after taking input for the proposed architecture is 18.514 ns and the currently operating frequency is 54 MHz.
“…It can be observed from Table 2 that the proposed architecture has a lower gate count than that from [9] and [10] but not [5] and [11]; however, clock cycles required by [5] and [11] are much greater than the proposed one. [10] achieved fewer clock cycles at the cost of using large size memories and higher gate count.…”
Section: Implementation Results Of the Proposed Architecturementioning
confidence: 94%
“…[10] achieved fewer clock cycles at the cost of using large size memories and higher gate count. The resolution used in [5] is 1080p and is four times less than that of all the other architectures. We have achieved a faster architecture in our design than [5] but at the stake of larger gate count.…”
Section: Implementation Results Of the Proposed Architecturementioning
confidence: 99%
“…The resolution used in [5] is 1080p and is four times less than that of all the other architectures. We have achieved a faster architecture in our design than [5] but at the stake of larger gate count. The main reason for the better results of the proposed architecture is the use of small size distributed memories and parallel filtering.…”
Section: Implementation Results Of the Proposed Architecturementioning
confidence: 99%
“…The filtering in HEVC is less complex and more efficient than the deblocking filter of the previous H.264 standard [5]. The DBF in HEVC employs parallel filtering to improve subjective and objective quality by suppressing and removing blocking artifacts [6].…”
This paper proposes the architecture of a deblocking filter (DBF) that removes blocking artifacts in new emerging High Efficiency Video Coding (HEVC). A parallel architecture for both normal and strong filtering modes of HEVC is proposed. Distributed memories and two data paths increase the parallelism and make the architecture more efficient. The proposed architecture is described by Verilog and implemented on FPGA. The architecture can realize real time to compute 4K UHD video at 30 fps by using 46.65 million clocks with total equivalent gate count of 46K. The maximum delay time for output to come after taking input for the proposed architecture is 18.514 ns and the currently operating frequency is 54 MHz.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.