Plant leaf identification system using convolutional neural network

This paper proposes a leaf identification system using convolutional neural network (CNN). This proposed system can identify five types of local Malaysia leaf which were acacia, papaya, cherry, mango and rambutan. By using CNN from deep learning, the network is trained from the database that acquired from leaf images captured by mobile phone for image classification. ResNet-50 was the architecture has been used for neural networks image classification and training the network for leaf identification. The recognition of photographs leaves requested several numbers of steps, starting with image pre-processing, feature extraction, plant identification, matching and testing, and finally extracting the results achieved in MATLAB. Testing sets of the system consists of 3 types of images which were white background, and noise added and random background images. Finally, interfaces for the leaf identification system have developed as the end software product using MATLAB app designer. As a result, the accuracy achieved for each training sets on five leaf classes are recorded above 98%, thus recognition process was successfully implemented.

Traffic extreme situations detection in video sequences based on integral optical flow

Road traffic analysis is an important task in many applications and it can be used in video surveillance systems to prevent many undesirable events. In this paper, we propose a new method based on integral optical flow to analyze cars movement in video and detect flow extreme situations in real-world videos. Firstly, integral optical flow is calculated for video sequences based on optical flow, thus random background motion is eliminated; secondly, pixel-level motion maps which describe cars movement from different perspectives are created based on integral optical flow; thirdly, region-level indicators are defined and calculated; finally, threshold segmentation is used to identify different cars movements. We also define and calculate several parameters of moving car flow including direction, speed, density, and intensity without detecting and counting cars. Experimental results show that our method can identify cars directional movement, cars divergence and cars accumulation effectively.

CFD Analysis of Deck Impact in Irregular Waves: Wave Representation by Transient Wave Groups

Analysis of wave structure interaction problems are increasingly handled by employing CFD methods such as the well known Volume-of-Fluid (VoF) method. In particular for the problem of deck impact on fixed structures with slender substructures, CFD methods have been used extensively in the last few years. For this case, the initial conditions have usually been treated as regular waves in an undisturbed wave field which may be given accurately as input. As CFD analyses become more widely available and are used for more complex problems it is also necessary to consider the problem of irregular waves in a CFD context. Irregular waves provide a closer description of the sea surface than regular waves and are also the chief source of statistical variability in the wave induced loading level. In general, it is not feasible to run a long simulation of an irregular seastate in a CFD analysis today since this would require very long simulation times and also a very large computational domain and sophisticated absorbing boundary conditions to avoid build-up of reflections in the domain. The present paper is concerned with the use of a single transient wave group to represent a large event in an irregular wave group. It is well known that the autocovariance function of the wave spectrum is proportional to the mean shape of a large wave in a Gaussian wave field. The transient nature of such a wave ensures that a relatively small wave is generated at the upwave boundary and dissipated at the downwave boundary compared with the wave in the centre of the domain. Furthermore, a transient wave may be embedded in a random background if it is believed that the random background is important for the load level. The present paper describes the method of generating transient wave groups in a CFD analysis of wave in deck impact. The evolution of transient wave groups is first studied and compared with experimental measurements in order to verify that nonlinear transient waves can be calculated accurately using the present CFD code. Vertical wave induced loads on a large deck is then investigated for different undisturbed wave velocities and deck inundations.