Identifying crop water stress using deep learning models

Neural Computing and Applications - The identification of water stress is a major challenge for timely and effective irrigation to ensure global food security and sustainable agriculture. Several...     

A Method for Compact Image Representation Using Sparse Matrix and Tensor Projections Onto Exemplar Orthonormal Bases

We present a new method for compact representation of large image datasets. Our method is based on treating small patches from a 2-D image as matrices as opposed to the conventional vectorial representation, and encoding these patches as sparse projections onto a set of exemplar orthonormal bases, which are learned a priori from a training set. The end result is a low-error, highly compact image/patch representation that has significant theoretical merits and compares favorably with existing techniques (including JPEG) on experiments involving the compression of ORL and Yale face databases, as well as a database of miscellaneous natural images. In the context of learning multiple orthonormal bases, we show the easy tunability of our method to efficiently represent patches of different complexities. Furthermore, we show that our method is extensible in a theoretically sound manner to higher-order matrices (“tensors”). We demonstrate applications of this theory to compression of well-known color image datasets such as the GaTech and CMU-PIE face databases and show performance competitive with JPEG. Lastly, we also analyze the effect of image noise on the performance of our compression schemes.      

Development of an automated mobile robotic sprayer to prevent workers' exposure of agro-chemicals inside polyhouse

Automated spraying practices are inevitable for modern polyhouse management to attain a broader objective of minimizing human exposure to agrochemicals. In the present study, an automated mobile robotic sprayer (AMRS) was developed to combat the increased human intervention and safeguard agricultural workers from potential health hazards. The system mainly comprises embedded sensors (ultrasonic, proximity, XBee) and controllers (Arduino, PLC). The controller drives the system on a piping track between the rows as well as on the head space achieving end-to-end automation for spraying operations. The system performance was evaluated on the tomato crop with respect to the physiological traits, yield and economics. Additionally, the study leveraged response surface methodology to optimize forward speed, spray distance, and working pressure of AMRS on the responses, droplet density, coverage, volume mean diameter (VMD) and application rate. Optimization of forward speed (0.79 km/h), spray distance (250 mm) and working pressure (0.40 MPa) resulted in 90.7 droplets/cm² droplet density, 47.1% coverage, 170.2 μm VMD and 86.0 mL/m² of application rate. Ergonomic aspects of AMRS were assessed by the parameters, human exposure, discomfort and postural assessment with respect to knapsack sprayer. The working heart rate of 103 beats/min, work pulse of 12 beats/min, oxygen consumption rate of 916 mL/min and energy expenditure rate of 18.7 kJ/min recorded during the ergonomic evaluation of the AMRS were 25%, 75%, 42%, and 41% lower compared to manual spraying, respectively. Moreover, three–six times higher work pulse, cardiac cost, body part discomfort score and overall discomfort rating were observed which indicated more drudgery involved in manual spraying. State-of-the-art system developed for polyhouses would minimize the drudgery and health hazards, significantly. The system's resilience and effectiveness pave the way for its wider deployment where the use of agrochemicals are prevalent, particularly in small-size polyhouses.     

Three-dimensional view-invariant face recognition using a hierarchical pose-normalization strategy

Face recognition from three-dimensional (3D) shape data has been proposed as a method of biometric identification as a way of either supplanting or reinforcing a two-dimensional approach. This paper presents a 3D face recognition system capable of recognizing the identity of an individual from a 3D facial scan in any pose across the view-sphere, by suitably comparing it with a set of models (all in frontal pose) stored in a database. The system makes use of only 3D shape data, ignoring textural information completely. Firstly, we propose a generic learning strategy using support vector regression [Burges, Data Mining Knowl Discov 2(2): 121–167, 1998] to estimate the approximate pose of a 3D head. The support vector machine (SVM) is trained on range images in several poses belonging to only a small set of individuals and is able to coarsely estimate the pose of any unseen facial scan. Secondly, we propose a hierarchical two-step strategy to normalize a facial scan to a nearly frontal pose before performing any recognition. The first step consists of either a coarse normalization making use of facial features or the generic learning algorithm using the SVM. This is followed by an iterative technique to refine the alignment to the frontal pose, which is basically an improved form of the Iterated Closest Point Algorithm [Besl and Mckay, IEEE Trans Pattern Anal Mach Intell 14(2):239–256, 1992]. The latter step produces a residual error value, which can be used as a metric to gauge the similarity between two faces. Our two-step approach is experimentally shown to outperform both of the individual normalization methods in terms of recognition rates, over a very wide range of facial poses. Our strategy has been tested on a large database of 3D facial scans in which the training and test images of each individual were acquired at significantly different times, unlike all except two of the existing 3D face recognition methods.