Recent progress in innovation is making the life prosper, simpler and easier for common individual. The World Health Organization (WHO) statistics indicate that a large amount of people experience visual losses, because of which they encounter many difficulties in everyday jobs. Hence, our goal is to structure a modest, secure, wearable, and versatile framework for visually impaired to help them in their daily routines. The proposed methodology utilizes Raspberry-Pi 4B, Camera, Ultrasonic Sensor and Arduino, mounted on the stick of the individual. We take pictures of the scene and afterwards pre-process these pictures with the help of Viola Jones and TensorFlow Object Detection algorithm. The said techniques are used to detect objects. We also used an ultrasonic sensor mounted on a servomotor to measure the distance between the blind person and obstacles. The presented research utilizes simple calculations for its execution, and detects the obstructions with a notably high efficiency. When contrasted with different frameworks, this framework is a minimal effort, convenient, and simple to wear.

Smart Assistive System for Visually Impaired People Obstruction Avoidance through Object Detection and Classification

Structural obfuscation offers a means to effectively secure through obfuscation the contents of an intellectual property (IP) cores used in an electronic system-on-chip (SoC). In this work a novel structural obfuscation methodology for protecting a digital signal processor (DSP) IP core at the architectural synthesis design stage. The proposed approach specifically targets protection of IP cores that involve complex loops. Five different algorithmic level transformation techniques are employed: loop unrolling, loop invariant code motion, tree height reduction/increment, logic transformation and redundant operation removal. Each of these can yield camouflaged functionally equivalent designs. In addition, low cost obfuscated design is generated through proposed approach through the use of multi-stage algorithmic transformation and particle swarm optimization (PSO)-drive design space exploration (DSE). Results of proposed approach yielded an enhancement obfuscation of 22 % and reduction in obfuscated design cost of 55 % compared to similar prior art.

DSP design protection in CE through algorithmic transformation based structural obfuscation

In recent years, man has become more aware of the fact that today’s approach to energy saving is unsustainable. It is believed that in the near future, biomass will increasingly become of interest as one of the most promising renewable energy sources. The paper describes one example of the use of biomass (corn cob) in the process of production of thermal energy, i.e. in the process of seedcorn drying. The purpose of the investigations reported in the paper was to define the use of corn cob as a fuel to increase energy efficiency. Additionally, energy efficiency was explained through hourly consumption of corn cob in thermogens, which was further compared with consumption of conventional fuels (natural gas).

Energy efficiency analysis of corn cob used as a fuel

Automated generation, or completion, or checking of source code is described whereby a probabilistic model having been trained using a corpus of natural source code examples is used. In various examples the probabilistic model comprises probability distributions describing belief about structure of natural source code and takes into account source code analysis from a compiler or other source code analyzer. In various examples, source code analysis may comprise syntactic structure, type information and other data about source code. In various examples, the trained probabilistic model is used to predict sequences of source code elements. For example, to generate source code, to auto-complete source code, to error check source code, to error correct source code or for other purposes.

Source code generation, completion, checking, correction

Managing user applications is provided. A visual model of user interface display screens of a user application is generated by mapping components displayed within the user interface display screens to screen position coordinates and by mapping the screen position coordinates corresponding to the components to original source code of the user application. A runtime policy for each component in a selected set of components within the user interface display screens of the user application is generated based on user interaction with the generated visual model of the user interface display screens. The generated runtime policy for each component in the selected set of components is sent to a client device via a network. Activity of each component in the selected set of components in the client device is tracked using data that is tracked and logged on the client device based the generated runtime policy for each selected component.

Automatic extraction, modeling, and code mapping of application user interface display screens and components

Generating source code from a model, using a model-driven development techniques (MDD), rapidly increases application reliability and substantially accelerates time-to-market, thereby reducing application development costs. The generated source code does not have its functional implementation, so besides MDD, it is necessary to create some additional tools that will fulfill this gap. This paper describes a design of a system for automatic model development and automatic source code generation that transforms specification into the product implementation. Specification contains data necessary for the implementation of GUI controls. Controls are integrated as a part of an Eclipse based IDE. To reduce the amount of source code that needs to be generated, reflection API Java feature is used. Reflection API is also used for developing JUnit Java tests, that verify the reliability of generated source code. Using the proposed algorithm 1960 GUI controls and 3920 JUnit tests are generated. Based on this approach it is estimated that time-to-market is reduced four and a half months and quality of source code is increased significantly, lowering the total cost of developing and maintaining application.

An approach to model driven development and automatic source code generation of GUI controls

Since neural networks were first introduced into automotive systems, safety has been a major concern. The prevailing safety standard in the automotive industry, ISO26262, does not fully define testing and verification methods for software based on deep learning. In this paper, we propose a multiunit perception framework that increases the determinism of automotive systems incorporating deep learning. Our approach relies on ASIL decomposition and algorithm diversification, which are enabled through the utilization of multiple low ASIL perception units and one high ASIL monitor unit. In addition to the framework concept, we specify how each component can be mapped to appropriate hardware and software platforms. The practical feasibility of the perception framework is demonstrated with a proof of concept prototype.

Multiunit automotive perception framework: Synergy between AI and deterministic processing

Keeping vehicle in the right track while driving is common task for humans, as they perceive lane lines with ease. Naturally, one of the essential tasks for autonomous vehicle would be to detect lane lines. Except for using them as constant reference in steering controller, they are used as inputs in other driver assistance functions like lane departure warning, for example. Different road and weather conditions make it difficult to detect lane lines, as marking can become indistinct or disappear. Many simple vision-based algorithms rely on detection of edges of the markings with Canny edge detection and previously mentioned problems can affect proper extrapolation of lanes. This paper also belongs to vision-based group of algorithms that use camera. It presents usage of color thresholding to detect lane edges and together with perspective transformations and Hough transform to extrapolate lane segments in image with controlled conditions. These conditions include straight road and sunny weather. We used OpenCV computer vision framework that supports mentioned functionalities and algorithms, with Python, to obtain and compare results.

Vision-Based Extrapolation of Road Lane Lines in Controlled Conditions

Higher levels of autonomous driving are bringing sophisticated requirements and unpredicted challenges. In order to solve these problems, the set of functionalities in modern vehicles is growing in terms of algorithmic complexity and required hardware. The risk of testing implemented solutions in real world is high, expensive and time consuming. This is the reason for virtual automotive simulation tools for testing are heavily acclaimed. Original Equipment Manufacturers (OEMs) use these tools to create closed sense, compute, act loop to have realistic testing scenarios. Production software is tested against simulated sensing data. Based on these inputs a set of actions is produced and simulated which generates consequences that are evaluated. This creates a possibility for OEMs to minimize design errors and optimize costs of the vehicle production before any physical prototypes are produced. This paper presents the development of simple C++/Python perception applications that can be used in driver assistance functionalities. Using ROS as a prototyping platform these applications are validated and tested with "Software-In-the Loop" (SIL) method. CARLA simulator is used as a generator for input data and output commands of the autonomous platform are executed as simulated actions within simulator. Validation is done by connecting Autoware autonomous platform with CARLA simulator in order to test against various scenes in which applications are applicable. Vision based lane detection, which is one of the prototypes, is also tested in a real world scenario to demonstrate the applicability of algorithms developed with simulators to real-time processing

/pdf/development-of-adas-perception-applications-in-ros-and-21ng0ho2vi.pdf

Development of ADAS perception applications in ROS and "Software-In-the-Loop" validation with CARLA simulator

The aim of this paper is to prove the generic nature of a framework used for deployment, debugging and control of DSP applications. The central part of the framework is a debug proxy server with a target independent debug interface. We present an expansion of the proxy server to support debugging applications on a server-based virtual platform by using the same debug interface.

https://ieeexplore.ieee.org/iel7/7861953/7867133/07867148.pdf

Momcilo Krunic

Papers

An approach to model driven development and automatic source code generation of GUI controls

Multiunit automotive perception framework: Synergy between AI and deterministic processing

Vision-Based Extrapolation of Road Lane Lines in Controlled Conditions

Development of ADAS perception applications in ROS and "Software-In-the-Loop" validation with CARLA simulator

Debug proxy server for DSP platforms