Search

Weed detection has become an integral part of precision farming that leverages the IoT framework. Weeds have become responsible for 45% of the agriculture industry's crop losses due mainly to the competition with crops. An efficient weed detection method can reduce this percentage. This paper proposes a vision-based weed detection system using deep learning models that effectively detect weed within a soybean plantation. Five deep learning models are used, including MobileNetV2, ResNet50, and three custom Convolutional Neural Network (CNN) Models. The MobileNetV2 and ResNet50 were deployed on a Raspberry PI controller for comparison purposes. Based on a dataset with 400 images and 1536 total segments, the custom 5-layer CNN architecture shows high detection accuracy of 97.7% and the lowest latency & memory usage with 1.78 GB and 22.245 ms respectively. Utilizing the proposed custom deep learning CNN model with high accuracy can positively impact efficiency, time, and overall production within the soybean industry.

Detection of the surrounding objects of a vehicle is the most crucial step in autonomous driving. Failure to identify those objects correctly in a timely manner can cause irreparable damage, impacting our safety and society. Several studies have been introduced to identify these objects in the two-dimensional (2D) and three-dimensional (3D) vector space. The 2D object detection method has achieved remarkable success; however, in the last few years, detecting objects in 3D have received more remarkable adoption. 3D object recognition has several advantages over 2D detection methods, as more accurate information about the environment is obtained for better detection. For example, the depth of the images is not considered in the 2D detection, which reduces the detection accuracy. Despite considerable efforts in 3D object detection, it has not yet reached the stage of maturity. Therefore, in this paper, we aim at providing a comprehensive overview of the state-of-the-art 3D object detection methods, with a focus on 1) identifying advantages and limitations, 2) revelling a novel categorization of the literature, 3) outlying the various training procedures, 4) highlighting the research gap in the existing methods and 5) building a road map for future directions.

By developing cities and increasing population, smart transportation becomes an essential component of modern societies. Extensive research activities using machine learning techniques and several industrial needs have paved the way for the emerging field of smart transportation. This paper presents data, methods, and models that are essential for intelligent planning of transportation. In particular, the current data sources for gathering information to control or forecast traffic are described, connected Vehicles (CVs) that bring smart and green transportation to modern life is also discussed. Clustering Analysis as an effective unsupervised machine learning method in trip distribution and generation and traffic zone division is discussed in the paper. Various machine learning techniques and models that use time series prediction are introduced in this paper including ARIMA, Kalman filtering, Holt winters'Exponential smoothing, Random walk, KNN Algorithm, and Deep Learning. Finally, a discussion on the main advantages and drawbacks of these models, as well as the business adoption of the forecasting models are presented.