A hardware/software co-design model for face recognition using Cognimem Neural Network chip

Sardar, Santu; Tewari, Gaurav; Babu, K. Ananda

doi:10.1109/iciip.2011.6108866

Cited by 22 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the system's ability to distinguish between occurrence of different types of changes in the environment. False Rejection Rate (FRR) or false negative rate (Type I Error) and false acceptance rate (FAR) or false positive rate (Type II Error) [21] are another two performance parameters for classification.…”

Section: B Vehicle Classificationmentioning

confidence: 99%

Vehicle detection and classification using LTE‐CommSense

Sardar

Mishra²,

Khan

2019

IET Radar, Sonar & Navigation

Self Cite

View full text Add to dashboard Cite

We demonstrated a vehicle detection and classification method based on Long Term Evolution (LTE) communication infrastructure based environment sensing instrument, termed as LTE-CommSense by the authors. This technology is a novel passive sensing system which focuses on the reference signals embedded in the sub-frames of LTE resource grid. It compares the received signal with the expected reference signal, extracts the evaluated channel state information (CSI) and analyzes it to estimate the change in the environment. For vehicle detection and subsequent classification, our setup is similar to a passive radar in forward scattering radar (FSR) mode. Instead of performing the radio frequency (RF) signals directly, we take advantage of the processing that happens in a LTE receiver user equipment (UE). We tap into the channel estimation and equalization block and extract the CSI value. CSI value reflects the property of the communication channel between communication base station (eNodeB) and UE. We use CSI values for with and vehicle and without vehicle case in outdoor open road environment. Being a receiver only system, there is no need for any transmission and related regulations. Therefore, this system is low cost, power efficient and difficult to detect. Also, most of its processing will be done by the existing LTE communication receiver (UE). In this paper, we establish our claim by analyzing field-collected data. Live LTE downlink (DL) signal is captured using modeled LTE UE using software defined radio (SDR). The detection analysis and classification performance shows promising results and ascertains that, LTE-CommSense is capable of detection and classification of different types of vehicles in outdoor road environment.

show abstract

Section: B Vehicle Classificationmentioning

confidence: 99%

Vehicle detection and classification using LTE‐CommSense

Sardar

Mishra²,

Khan

2019

IET Radar, Sonar & Navigation

Self Cite

View full text Add to dashboard Cite

show abstract

“…But common PCA-based methods has two limitations: poor discriminatory power and large computational load [3]. On the other hand, the time-frequency image (TFI) constructed using the phase information of the SAR signal can provide effective features of each target and can improve the correct classification [6].…”

Section: Introductionmentioning

confidence: 99%

A robust and efficient SAR ATR algorithm using a hybrid model of fractional fourier transform and pulse coupled neural network

Sardar¹,

Mishra²

2014

2014 IEEE International Microwave and RF Conference (IMaRC)

Self Cite

View full text Add to dashboard Cite

A hybrid framework consisting of Fractional Fourier Transform (FrFT) and Pulse coupled Neural network (PCNN) is proposed in this paper for highly accurate and orientation, position & scale invariant synthetic aperture radar (SAR) automatic target recognition (ATR). FrFT is used to gather scattering information and insights that are attainable using timefrequency and time-scale techniques, whereas PCNN is used to achieve invariant target recognition. Public release of the MSTAR dataset is used to validate the proposed system. We compared our proposed system performance with existing approaches and established the better performance of this system. We have shown that, even with reduced training sets, the proposed system shows consistent performance whereas the performance of conventional systems degrades.

show abstract

“…Neural networks also make no prior assumption about the profile of input data and can construct complex decision boundaries. Recent advances in neuromorphic hardware 4 have led to increased interest due to their superior performance in processing massively parallel tasks such as pattern recognition, 5 and its potential to fully leverage the non-Von Neumann architectural nature of neural networks. 6 In this research, we sought to demonstrate the feasibility of enhancing the intelligence of UAVs by exploring an autonomous online target tracking methodological framework, based on high-performance, ultra-low-power neural network hardware.…”

Section: Introductionmentioning

confidence: 99%

Autonomous target tracking of UAVs based on low-power neural network hardware

et al. 2014

View full text Add to dashboard Cite

Detecting and identifying targets in unmanned aerial vehicle (UAV) images and videos have been challenging problems due to various types of image distortion. Moreover, the significantly high processing overhead of existing image/video processing techniques and the limited computing resources available on UAVs force most of the processing tasks to be performed by the ground control station (GCS) in an off-line manner. In order to achieve fast and autonomous target identification on UAVs, it is thus imperative to investigate novel processing paradigms that can fulfill the real-time processing requirements, while fitting the size, weight, and power (SWaP) constrained environment. In this paper, we present a new autonomous target identification approach on UAVs, leveraging the emerging neuromorphic hardware which is capable of massively parallel pattern recognition processing and demands only a limited level of power consumption. A proof-of-concept prototype was developed based on a micro-UAV platform (Parrot AR Drone) and the CogniMem TM neural network chip, for processing the video data acquired from a UAV camera on the fly. The aim of this study was to demonstrate the feasibility and potential of incorporating emerging neuromorphic hardware into next-generation UAVs and their superior performance and power advantages towards the real-time, autonomous target tracking.

show abstract

A hardware/software co-design model for face recognition using Cognimem Neural Network chip

Cited by 22 publications

References 15 publications

Vehicle detection and classification using LTE‐CommSense

Vehicle detection and classification using LTE‐CommSense

A robust and efficient SAR ATR algorithm using a hybrid model of fractional fourier transform and pulse coupled neural network

Autonomous target tracking of UAVs based on low-power neural network hardware

Contact Info

Product

Resources

About