Sai Manoj Prakhya

Bio: Sai Manoj Prakhya is an academic researcher from Nanyang Technological University. The author has contributed to research in topics: Feature (computer vision) & Wheelchair. The author has an hindex of 7, co-authored 13 publications receiving 215 citations. Previous affiliations of Sai Manoj Prakhya include Amrita Vishwa Vidyapeetham & Institute for Infocomm Research Singapore.

Wireless vehicular Accident Detection and Reporting System

Abstract: In this paper, we suggest a method to intelligently detect an accident at any place and any time and report the same to the nearby ‘service provider’. The service provider arranges for the necessary help. Accident Detection and Reporting System (ADRS) which can be placed in any vehicle uses a sensor to detect the accident. The sensor output is monitored and processed by the PIC16F877A microcontroller. The microcontroller takes decision on the traffic accident based on the input from the sensors. The RF transmitter module which is interfaced with the microcontroller will transmit the accident information to the nearby Emergency Service Provider (ESP). This information is received by the RF receiver module at the ‘service provider’ control room in the locality. The RF transceiver module used has a range up to 100 meters under ideal conditions. The service provider can use this information to arrange for ambulance and also inform police and hospital. We used low cost RF modules, a microcontroller by Microchip, LCD module and an accelerometer. This system can be installed at accident prone areas to detect and report the same. MPLAB IDE and Proteus software are used to simulate part of the system. ADRS also implements an intelligent Accident Detection and Reporting Algorithm (ADRA) for the purpose.

B-SHOT: A binary feature descriptor for fast and efficient keypoint matching on 3D point clouds

Abstract: In this paper, we introduce the very first ‘binary’ 3D feature descriptor, B-SHOT, for fast and efficient keypoint matching on 3D point clouds. We propose a binary quantization method that converts a real valued vector to a binary vector. We apply this method on a state-of-the-art 3D feature descriptor, SHOT [1], and create a new binary 3D feature descriptor. B-SHOT requires 32 times lesser memory for its representation while being 6 times faster in feature descriptor matching, when compared to the SHOT feature descriptor. Experimental evaluation shows that B-SHOT offers comparable keypoint matching performance to that of the state-of-the-art 3D feature descriptors on a standard benchmark dataset.

Automated voice based home navigation system for the elderly and the physically challenged

Abstract: In this paper, we propose an Intelligent Home Navigation System (IHNS) which comprises of a wheelchair, voice module and navigation module It can be used by an elderly or physically challenged person to move inside the home without any difficulty It's common that the elders forget the way to the different rooms in house and the physically challenged people find it hard to move the wheel chair without external aid By making use of IHNS, elderly and the physically challenged can go to different rooms in the house like kitchen, living room, dining room etc by just speaking a word which is predefined to that particular room The voice of the person is detected by voice capture module which will be compared by voice recognition module with predefined voices loaded in to the system According to the received voice, the destination is automatically understood and the wheelchair moves according to the route which is predefined It is also equipped with obstacle avoidance technique, where the person may not be able to provide proper voices at the right time The wheel chair can automatically navigate from one point to the other in the home as per predefined route based on the voice received Thus the above proposed system can be used by elderly and physically challenged people in day to day life even if they are alone at home

B-SHOT: a binary 3D feature descriptor for fast Keypoint matching on 3D point clouds

Abstract: We present the first attempt in creating a binary 3D feature descriptor for fast and efficient keypoint matching on 3D point clouds. Specifically, we propose a binarization technique and apply it on the state-of-the-art 3D feature descriptor, SHOT (Salti et al., Comput Vision Image Underst 125:251–264, 2014) to create the first binary 3D feature descriptor, which we call B-SHOT. B-SHOT requires 32 times lesser memory for its representation while being six times faster in feature descriptor matching, when compared to the SHOT feature descriptor. Next, we propose a robust evaluation metric, specifically for 3D feature descriptors. A comprehensive evaluation on standard benchmarks reveals that B-SHOT offers comparable keypoint matching performance to that of the state-of-the-art real valued 3D feature descriptors, albeit at dramatically lower computational and memory costs.

3DHoPD: A Fast Low-Dimensional 3-D Descriptor

Abstract: Three-dimensional feature descriptors are heavily employed in various 3-D perception applications to find keypoint correspondences between two point clouds. The availability of mobile devices equipped with depth sensors compels the developed applications to be both memory and computationally efficient. Toward this, in this letter, we present 3DHoPD, a new low-dimensional 3-D feature descriptor that is extremely fast to compute. The novelty lies in compactly encoding the “3-D” keypoint position by transforming it to a new 3-D space, where the keypoints arising from similar 3-D surface patches lie close to each other. Then, we propose histograms of point distributions (HoPD) to capture the neighborhood structure, thus forming 3DHoPD (3D+HoPD). We propose a tailored feature descriptor matching technique, wherein the “3-D” keypoint position in the new 3-D space is used to remove false positive matches, effectively reducing the search space by 90%, and then, the exact match is found using the “HoPD” descriptor. Experimental evaluation on multiple publicly available datasets shows that 3DHoPD is robust to noise and offers stable and competitive keypoint matching performance to the existing state-of-the-art 3-D descriptors with similar dimensionality across datasets, while requiring dramatically low-computational time (10 $\times$ faster). The source code and additional experimental results are available at https://sites.google.com/site/3dhopd/

Accident detection and reporting system using GPS, GPRS and GSM technology

Abstract: Speed is one of the basic reasons for vehicle accident. Many lives could have been saved if emergency service could get accident information and reach in time. Nowadays, GPS has become an integral part of a vehicle system. This paper proposes to utilize the capability of a GPS receiver to monitor speed of a vehicle and detect accident basing on monitored speed and send accident location to an Alert Service Center. The GPS will monitor speed of a vehicle and compare with the previous speed in every second through a Microcontroller Unit. Whenever the speed will be below the specified speed, it will assume that an accident has occurred. The system will then send the accident location acquired from the GPS along with the time and the speed by utilizing the GSM network. This will help to reach the rescue service in time and save the valuable human life.

A novel binary shape context for 3D local surface description

Abstract: 3D local surface description is now at the core of many computer vision technologies, such as 3D object recognition, intelligent driving, and 3D model reconstruction. However, most of the existing 3D feature descriptors still suffer from low descriptiveness, weak robustness, and inefficiency in both time and memory. To overcome these challenges, this paper presents a robust and descriptive 3D Binary Shape Context (BSC) descriptor with high efficiency in both time and memory. First, a novel BSC descriptor is generated for 3D local surface description, and the performance of the BSC descriptor under different settings of its parameters is analyzed. Next, the descriptiveness, robustness, and efficiency in both time and memory of the BSC descriptor are evaluated and compared to those of several state-of-the-art 3D feature descriptors. Finally, the performance of the BSC descriptor for 3D object recognition is also evaluated on a number of popular benchmark datasets, and an urban-scene dataset is collected by a terrestrial laser scanner system. Comprehensive experiments demonstrate that the proposed BSC descriptor obtained high descriptiveness, strong robustness, and high efficiency in both time and memory and achieved high recognition rates of 94.8%, 94.1% and 82.1% on the considered UWA, Queen, and WHU datasets, respectively.

Brain Computer Interfaces for Improving the Quality of Life of Older Adults and Elderly Patients.

Abstract: All people experience aging, and the related physical and health changes, including changes in memory and brain function. These changes may become debilitating leading to an increase in dependence as people get older. Many external aids and tools have been developed to allow older adults and elderly patients to continue to live normal and comfortable lives. This mini-review describes some of the recent studies on cognitive decline and motor control impairment with the goal of advancing non-invasive brain computer interface (BCI) technologies to improve health and wellness of older adults and elderly patients. First, we describe the state of the art in cognitive prosthetics for psychiatric diseases. Then, we describe the state of the art of possible assistive BCI applications for controlling an exoskeleton, a wheelchair and smart home for elderly people with motor control impairments. The basic age-related brain and body changes, the effects of age on cognitive and motor abilities, and several BCI paradigms with typical tasks and outcomes are thoroughly described. We also discuss likely future trends and technologies to assist healthy older adults and elderly patients using innovative BCI applications with minimal technical oversight.

LiDAR Iris for Loop-Closure Detection

Abstract: In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection. A binary signature image can be obtained for each point cloud after several LoG-Gabor filtering and thresholding operations on the LiDAR-Iris image representation. Given two point clouds, their similarities can be calculated as the Hamming distance of two corresponding binary signature images extracted from the two point clouds, respectively. Our LiDAR-Iris method can achieve a pose-invariant loop-closure detection at a descriptor level with the Fourier transform of the LiDAR-Iris representation if assuming a 3D (x,y,yaw) pose space, although our method can generally be applied to a 6D pose space by re-aligning point clouds with an additional IMU sensor. Experimental results on five road-scene sequences demonstrate its excellent performance in loop-closure detection.