Artificial intelligence in vision based approaches have proven to be effective in various phases of intelligent vehicle system (IVS). An IVS has to intelligently take many critical decisions in heterogeneous environment. Speed bump detection is one such issue in real world due to its varying appearance in dynamic scene. The major issue is the scaling appearance of such objects from far distance and often viewed as small entity. In the proposed article, deep learning and computer vision based speed bump detection model is proposed, which assist and control the driving behavior of an IVS before it reaches to speed bump. The behavior of IVS has been explored and tested by incorporating the proposed method with a real time embedded prototype and found to be more efficient and comparable with state-of-art techniques. The overall performance of the proposed model has been achieved in terms of accuracy, precision and F-Measure as 98.54%, 99.05% and 97.89% respectively in the prepared real time environment.

Deep Learning-Based Speed Bump Detection Model for Intelligent Vehicle System Using Raspberry Pi

Lane detection on the road is the most essential phase of existing advanced driver assistance systems (ADAS). In the current road scheme, the lanes are parallel tracks which are marked based on the different speed limit for the vehicles. Lane markings are defined as driving regions for the vehicles in order to avoid a collision. In an Intelligent Vehicle System (IVS), these markings are being identified by various massive computing techniques and sensor-based mechanisms like radar, LiDAR, and GPS and have high operational costs. However, vision-based detection methods are gaining popularity due to its low cost and better understanding capability of the scene. The proposed study follows computer vision and image processing techniques to examine and learn significant lane features. The approach demonstrates the practical and effective usage of the lane detection model (LDM). The LDM has been designed with a vehicle prototype using Raspberry Pi, which reveals the intelligent behavior against the detected lane lines. The model is less expensive and power-efficient, which confirms the operational capability of the proposed system under a heterogeneous environment.

Driving Behavior Analysis of Intelligent Vehicle System for Lane Detection Using Vision-Sensor

Recommendation systems have become very popular in recent years and are used in various web applications. Modern recommendation systems aim at providing users with personalized recommendations of online products or services. Various recommendation techniques, such as content-based, collaborative ﬁltering-based, knowledge-based, and hybrid-based recommendation systems, have been developed to fulﬁll the needs in different scenarios. This paper presents a comprehensive review of historical and recent state-of-the-art recommendation approaches, followed by an in-depth analysis of groundbreaking advances in modern recommendation systems based on big data. Furthermore, this paper reviews the issues faced in modern recommendation systems such as sparsity, scalability, and diversity and illustrates how these challenges can be transformed into proliﬁc future research avenues.

A Survey on Modern Recommendation System based on Big Data

Semantic segmentation as a pixel-wise segmentation task provides rich object information, which is an important research topic in robotic perception. It has been widely applied in many fields, such as autonomous driving and robot navigation. In the application of understanding road scene, the semantic segmentation model should accurately describe the appearance and shape of different categories of objects. In addition, the semantic segmentation model need to understand the spatial relationships between different categories. In order to improve the performance of semantic segmentation model for road scene, we present a model based on encoder-decoder structure with dilated convolution. We apply this model on the Cityscapes dataset and compare it with other classical models. To assess performance, we rely on the standard Jaccard Index IoU (Intersection over Union) and mIoU (mean Intersection over Union). The experimental results verify that this model can effectively improve the performance of semantic segmentation and meet the requirements for road scene.

Semantic Segmentation Model for Road Scene Based on Encoder-Decoder Structure

In this paper, we consider various constraints to generate a recommended speed profile for the covered path of the mobile robot, and use the recommended speed profile as the control input to complete trajectory tracking. These speeds are affected by the constraints of the robot's kinematics and dynamics model and the constraints of the robot's environment. The speed planner is used in many scenarios of mobile robots, such as cleaning robots, disinfecting robots, etc., which can improve the safety and efficiency of tasks performed by robots. We introduce the commonly used traffic regulations in daily life into the generation of speed profile. In certain sections of highways or urban roads, there will be a road sign indicating the recommended speed of the section. And our paper is to generate the speed of each point for the given path as the recommended speed for the robot to drive for reference. We use a dynamic window method to update the current environment in real-time. And calculate the influence of the environment in the window on the current speed. Then we use a pure pursuit method to track the given path, and we define a safety cost function to express the safety of the trajectory. We demonstrated the efficiency and security of this method by using a simulation platform.

An Intelligent Speed-Suggestion Planner for Coverage Path with Multiple Constraints

Since it is difficult to work out a complete and accurate analytical model for some complex nonlinear dynamical systems, we mainly propose a method for learning stable control with fast adaptive neural network. Furthermore, we provide a rigorous analytical evaluation of our proposed method in terms of stability. In order to validate the theoretical analysis, our proposed method has been applied in the stable control of a wheeled inverted pendulum (WIP) platform. It achieves high prediction accuracy and fast learning speed. In addition, the proposed method has incremental learning capabilities. When a new instance is provided, there is no need to retrain the entire training set, thus, the controller is more effective and more generalized.

Yuanzhe Peng

Papers

Semantic Segmentation Model for Road Scene Based on Encoder-Decoder Structure

An Intelligent Speed-Suggestion Planner for Coverage Path with Multiple Constraints

Learning Stable Control for a Wheeled Inverted Pendulum with Fast Adaptive Neural Network