A 0.05pJ/Pixel 70fps FHD 1Meps Event-Driven Visual Data Processing Unit

Sauseng, Paul; Majumder, Turbo; Augustine, Charles; Malavasi, Andres; Usirikayala, S.; Kumar, Raghavan; Kollikunnel, J.; Chhabra, Siddhartha; Yada, Satish; Barajas, Maribel; Ornelas, C.; Lake, Dan; Khellah, Muhammad; Tschanz, Jim; De, Vivek

doi:10.1109/vlsicircuits18222.2020.9162948

Cited by 8 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: B Majority Functionmentioning

confidence: 99%

A 51.3 TOPS/W, 134.4 GOPS In-memory Binary Image Filtering in 65nm CMOS

Bose,

Singla,

Basu

2021

Preprint

View full text Add to dashboard Cite

Neuromorphic vision sensors (NVS) can enable energy savings due to their event-driven that exploits the temporal redundancy in video streams from a stationary camera. However, noise-driven events lead to the false triggering of the object recognition processor. Image denoise operations require memoryintensive processing leading to a bottleneck in energy and latency. In this paper, we present in-memory filtering (IMF), a 6T-SRAM in-memory computing based image denoising for event-based binary image (EBBI) frame from an NVS. We propose a non-overlap median filter (NOMF) for image denoising. An in-memory computing framework enables hardware implementation of NOMF leveraging the inherent read disturb phenomenon of 6T-SRAM. To demonstrate the energy-saving and effectiveness of the algorithm, we fabricated the proposed architecture in a 65nm CMOS process. As compared to fully digital implementation, IMF enables > 70× energy savings and a > 3× improvement of processing time when tested with the video recordings from a DAVIS sensor and achieves a peak throughput of 134.4 GOPS. Furthermore, the peak energy efficiencies of the NOMF is 51.3 TOPS/W, comparable with state of the art inmemory processors. We also show that the accuracy of the images obtained by NOMF provide comparable accuracy in tracking and classification applications when compared with images obtained by conventional median filtering.

show abstract

Section: B Majority Functionmentioning

confidence: 99%

A 51.3 TOPS/W, 134.4 GOPS In-memory Binary Image Filtering in 65nm CMOS

Bose,

Singla,

Basu

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It is worth mentioning that the proposed architecture does not support multi-bit images. However, the RGB images can be transformed to event-based binary images by detecting changes (events) at the same pixel across frames comparing both linear and logarithmic pixel intensities [192] and apply the proposed method for In this work, we have presented an approximate computing method to reduce the computation energy of a specific type of IoT system used for anomaly detection (e.g., in predictive maintenance, epileptic seizure detection, etc.). We introduce approximation at the very early stage of machine life where the machine works perfectly and increase the accuracy of data processing with time using dynamic network scaling.…”

Section: Discussionmentioning

confidence: 99%

“…At 1.2V and 65nm process node, the estimated energy number is 7.04pJ/cycle (energy ∝ V 2 dd and ∝ (process node) 2 ). [192] implements RoI along with the event Generation module, the energy improvement for the proposed approach will be more significant than 1.5× at the same technology node and lower supply voltage.…”

Section: Execution Time Calculationmentioning

confidence: 99%

Edge processing in IoT using approximate and in-memory computing

Bose¹

View full text Add to dashboard Cite

First and foremost, I am grateful and would like to express my sincere gratitude to my supervisor, Prof. Arindam Basu, for his continuous guidance, support, and suggestion throughout my Ph.D. in NTU. Without his vision and faith in me, I could not have come this far. He has been very supportive and had given me the freedom to explore various research directions from day one of my Ph.D. I am amazed and inspired by his immense inter-disciplinary knowledge and passion for research. He not only improvised my problem-solving skills but also taught me to communicate my thoughts to others concisely. I am incredibly fortunate to have him as a mentor in both academic and non-academic life. He is a person to look up to, and I am forever thankful to him for the opportunity he provided four years back and shaping my entire career.

show abstract

“…In this section, we will compare the performances of the proposed near-memory computing-based edge event-driven region proposal (EEDRP) approach and of the in-memory computing-based axis projection based region proposal (APBRP) approach with that of the conventional connecting component labeling (CCL) approach [97], [98], in terms of memory requirement, execution time, and energy consumption. We define first a list of symbols that will be used throughout this section.…”

Section: Comparison With CCL Approachmentioning

confidence: 99%

“…Table4.4 compares the performance of the proposed EBBI processor with the prior works published recently. Both this work and[98] are for event based image processing, while this work and the rest of the references listed in the table leverage the parallel in-memory computing techniques. For the IMC-based image restoration, we define 5 operations per pixel -average of four neighbours plus threshold comparison.…”

mentioning

confidence: 99%

Low-power circuits for neuromorphic vision sensor based internet of video things

Zhang¹

View full text Add to dashboard Cite

I would not have been able to finish my Ph.D. study and have led an enriched research life. He is always considerate and kind. Due to his trust in me, I have been allowed to explore various research topics. I am amazed and inspired by his immense inter-disciplinary knowledge as well as the endless passion for research. He not only improved my problem-solving skills but also taught me to communicate with others effectively. I am incredibly fortunate to have him as a mentor in both academic and non-academic life. He is really a great role model, and I am forever thankful to him for the opportunity he provided in the past years. Special thanks to my supervisor Prof. Gwee Bah Hwee for the final support of my thesis submission and all his kind help for the last journey of my Ph.D. period.

show abstract

A 0.05pJ/Pixel 70fps FHD 1Meps Event-Driven Visual Data Processing Unit

Cited by 8 publications

References 0 publications

A 51.3 TOPS/W, 134.4 GOPS In-memory Binary Image Filtering in 65nm CMOS

A 51.3 TOPS/W, 134.4 GOPS In-memory Binary Image Filtering in 65nm CMOS

Edge processing in IoT using approximate and in-memory computing

Low-power circuits for neuromorphic vision sensor based internet of video things

Contact Info

Product

Resources

About