Weed Classification from Natural Corn Field-Multi-Plant Images Based on Shallow and Deep Learning.

Crop and weed discrimination in natural field environments is still challenging for implementing automatic agricultural practices, such as weed control. Some weed control methods have been proposed. However, these methods are still restricted as they are implemented under controlled conditions. The development of a sound weed control system begins by recognizing the crop and the different weed plants presented in the field. In this work, a classification approach of Zea mays L. (Crop), narrow-leaf weeds (NLW), and broadleaf weeds (BLW) from multi-plant images are presented. Moreover, a large image dataset was generated. Images were captured in natural field conditions, in different locations, and growing stages of the plants. The extraction of regions of interest (ROI) is carried out employing connected component analysis (CCA), whereas the classification of ROIs is based on Convolutional Neural Networks (CNN) and compared with a shallow learning approach. To measure the classification performance of both methods, accuracy, precision, recall, and F1-score metrics were used. The best alternative for the weed classification task at early stages of growth and in natural corn field environments was the CNN-based approach, as indicated by the 97% accuracy value obtained.

Distortion Calculation Method Based on Image Processing for Automobile Lateral Mirrors.

The automobile lateral-view mirrors are the most important visual support for driver safety; therefore, it is important they have robust quality control. Typically, the distortion of a lateral-view mirror is measured using the JIS-D-5705 standard; however, this methodology requires an expert person to perform the measurements and calculations manually, which can induce measurement errors. In this work, a semi-automatic distortion calculation method based on image processing is presented. Distortion calculations of five commercial mirrors from different manufacturers were performed, and a comparative study was carried out between the JIS-D-5705 standard and the proposed method. Experimental results performed according to the JIS-D-5705 standard showed that all mirrors have a distortion lower than 5%, indicating that all meet the standard. On the other hand, the proposed method was able to detect that one of the mirrors presented an important distortion, which was not detected by the methodology proposed in the standard; therefore, that mirror should not meet the standard. Then, it was possible to conclude that the proposed distortion calculation method, based on image processing, has higher robustness and precision than the standard. In addition, an appropriate and effective behavior against changes in scale, resolution, and, unlike the standard, against changes in image rotation was also shown.

Gait Activity Classification on Unbalanced Data from Inertial Sensors Using Shallow and Deep Learning.

Activity recognition is one of the most active areas of research in ubiquitous computing. In particular, gait activity recognition is useful to identify various risk factors in people's health that are directly related to their physical activity. One of the issues in activity recognition, and gait in particular, is that often datasets are unbalanced (i.e., the distribution of classes is not uniform), and due to this disparity, the models tend to categorize into the class with more instances. In the present study, two methods for classifying gait activities using accelerometer and gyroscope data from a large-scale public dataset were evaluated and compared. The gait activities in this dataset are: (i) going down an incline, (ii) going up an incline, (iii) walking on level ground, (iv) going down stairs, and (v) going up stairs. The proposed methods are based on conventional (shallow) and deep learning techniques. In addition, data were evaluated from three data treatments: original unbalanced data, sampled data, and augmented data. The latter was based on the generation of synthetic data according to segmented gait data. The best results were obtained with classifiers built with augmented data, with F-measure results of 0.812 (σ = 0.078) for the shallow learning approach, and of 0.927 (σ = 0.033) for the deep learning approach. In addition, the data augmentation strategy proposed to deal with the unbalanced problem resulted in increased classification performance using both techniques.