Despite all the significant advances in pedestrian detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions under which such a detector should operate, namely day and nighttime. Recent research has shown that the combination of visible and non-visible imaging modalities may increase detection accuracy, where the infrared spectrum plays a critical role. The goal of this paper is to assess the accuracy gain of different pedestrian models (holistic, part-based, patch-based) when training with images in the far infrared spectrum. Specifically, we want to compare detection accuracy on test images recorded at day and nighttime if trained (and tested) using (a) plain color images; (b) just infrared images; and (c) both of them. In order to obtain results for the last item, we propose an early fusion approach to combine features from both modalities. We base the evaluation on a new dataset that we have built for this purpose as well as on the publicly available KAIST multispectral dataset.

Despite recent significant advances, object detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities, and a strong multiview (MV) classifier that accounts for different object views and poses. In this paper, we provide an extensive evaluation that gives insight into how each of these aspects (multicue, multimodality, and strong MV classifier) affect accuracy both individually and when integrated together. In the multimodality component, we explore the fusion of RGB and depth maps obtained by high-definition light detection and ranging, a type of modality that is starting to receive increasing attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the accuracy, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient.

Summary: Root analysis is essential for both academic and agricultural research. Despite the great advances in root phenotyping and imaging, calculating root length is still performed manually and involves considerable amounts of labor and time. To overcome these limitations, we developed MyROOT, a software for the semiautomatic quantification of root growth of seedlings growing directly on agar plates. Our method automatically determines the scale from the image of the plate, and subsequently measures the root length of the individual plants. To this aim, MyROOT combines a bottom‐up root tracking approach with a hypocotyl detection algorithm. At the same time as providing accurate root measurements, MyROOT also significantly minimizes the user intervention required during the process. Using Arabidopsis, we tested MyROOT with seedlings from different growth stages and experimental conditions. When comparing the data obtained from this software with that of manual root measurements, we found a high correlation between both methods (R² = 0.997). When compared with previous developed software with similar features (BRAT and EZ‐Rhizo), MyROOT offered an improved accuracy for root length measurements. Therefore, MyROOT will be of great use to the plant science community by permitting high‐throughput root length measurements while saving both labor and time.