Monitoring, detection, and control of traffic is a serious problem in many cities and on roads around the world and poses a problem for effective and safe control and management of pedestrians with edge devices. Systems using the computer vision approach must ensure the safety of citizens and minimize the risk of traffic collisions. This approach is well suited for multiple object detection by automatic video surveillance cameras on roads, highways, and pedestrian walkways. A new Annotated Virtual Detection Line (AVDL) dataset is presented for multiple object detection, consisting of 74,108 data files and 74,108 manually annotated files divided into six classes: Vehicles, Trucks, Pedestrians, Bicycles, Motorcycles, and Scooters from the video. The data were captured from real road scenes using 50 video cameras from the leading video camera manufacturers at different road locations and under different meteorological conditions. The AVDL dataset consists of two directories, the Data directory and the Labels directory. Both directories provide the data as NumPy arrays. The dataset can be used to train and test deep neural network models for traffic and pedestrian detection, recognition, and counting.

In order to further increase efficiency while reducing harmful emissions, clever control methods have been proposed, e.g. using external electric and magnetic fields. We consider that minimalistic mathematical models are required if heat and mass transfer processes within the granule and the controlling device are low computational power. The authors develop the network model presented in previous publications, further preserving the topology of the network model, consisting of nodes and channels connecting the nodes, with one-dimensional gas dynamics equations governing the gas flow between the nodes. In addition, mass conservation laws are used at the nodes to couple the gas dynamics equations on the various nodes. The resistance to gas flow between the nodes in the two models is described by different parameters – permeability coefficient for the simple network model and channel length and diameter for the alternative model; these can be customized to apply both methods to the main problem. This paper deals with several stages of biomass granule production virtual material design process. At first, a network model describes the biomass granule’s internal structure, and heat, mass transfer, and chemical reaction processes are modeled on the network. Finally, we compare the results of the two models for some representative geometries. The results show good agreement if the network model is a sufficiently good discretization of the one-dimensional pipe network model. The results also depend on the geometry of the model.

The focus of this research is on the development of a network model for efficient simulation of the thermal conversion of heterogeneous biomass granules during gasification or combustion processes. The network model for heat and mass transport in a porous medium is constructed, which treats heterogeneous constituents of granules (such as wood and straw) as nodes and common surfaces as edges connect them and allow heat and mass to be transported. Reactions with Arrhenius kinetics are used to model the thermal decomposition of biomass. The gas is assumed to be an incompressible ideal gas flowing through a porous medium. A pressure correction scheme is used to model the mass transfer. Conductive and convective heat transfer equations with source terms are used for temperature modeling. Examples in 2D and 3D are presented. This network model can be used as a module in more complex biomass conversion models, such as the Lagrangian particle model in combination with the Eulerian model for fluid dynamics. Improved understanding of these complex processes contributes to enhancing the use of renewable resources, such as wood, straw, peat, for a variety of industry and household applications, leading to more carbon -neutral economy, as well as greater use of local resources.

The paper deals with a porous network model based simulation of effects of microwave pre-treatment of biomass pellets. Different heating regimesrapid and sloware compared; it is shown that rapid heating regime results in pressure build-up reaching values that cause breakage of the biomass material. Slow heating regime results in much lower maximum pressure values. As a second stage, ignition of pre-treated and non pretreated granules is compared. It is demonstrated that the pre-treated granule ignites considerably faster. The simulation considers intra-particle processes. The pellet is modelled as a porous material. The transport of volatiles is calculated using a nonlinear porous media equation. Thermal decomposition of the pellet is modelled using Arrhenius kinetics for three principal components of the biomass. An exponential rule for calculating the permeability of the material as a function of conversion rate is implemented. The model has been implemented in Octave. The result is a numerically cheap model that can be implemented and used to control the biomass gasification process. The model is versatile and can be extended to incorporate other physical and chemical processes.