Vertical farms are to be considered the future of agriculture given that they not only use space and resources efficiently but can also consistently produce large yields. Recently, artificial intelligence has been introduced for use in vertical farms to boost crop yields, and crop growth monitoring is an essential example of the type of automation necessary to manage a vertical farm system. Region of interest predictions are generally used to find crop regions from the color images captured by a camera for the monitoring of growth. However, most deep learning-based prediction approaches are associated with performance degradation issues in the event of high crop densities or when different types of crops are grown together. To address this problem, we introduce a novel method, termed pseudo crop mixing, a model training strategy that targets vertical farms. With a small amount of labeled crop data, the proposed method can achieve optimal performance. This is particularly advantageous for crops with a long growth period, and it also reduces the cost of constructing a dataset that must be frequently updated to support the various crops in existing systems. Additionally, the proposed method demonstrates robustness with new data that were not introduced during the learning process. This advantage can be used for vertical farms that can be efficiently installed and operated in a variety of environments, and because no transfer learning was required, the construction time for container-type vertical farms can be reduced. In experiments, we show that the proposed model achieved a performance of 76.9%, which is 12.5% better than the existing method with a dataset obtained from a container-type indoor vertical farm. Our codes and dataset will be available publicly.

Recent advances in artificial intelligence undeniably depend on vast amounts of high-quality data. However, a persistent global challenge is the restricted budgets allocated for data labeling. To address this, active learning emerges as a prominent and efficient strategy. It involves iterative selections of valuable data for labeling through a model and updating the model based on these selections. Nonetheless, the limited data available in each iteration renders the model susceptible to bias, resulting in potentially overconfident predictions. To mitigate this issue, we propose the Overcoming Overconfidence for Active Learning (OO4AL) framework. This framework comprises two parts: Cross-Mix-and-Mix, an augmentation strategy aimed at broadening the training distribution to calibrate the model, and Ranked Margin Sampling, a selection strategy that prevents the selection of overconfidence-inducing data by evaluating predictions. Through comprehensive experiments and analyses, we demonstrate that our framework facilitates efficient data selection by reducing overconfidence, though it can be readily implemented.

In this paper, multispectral pedestrian detection is mainly discussed, which can contribute to assigning human-aware properties to automated forklifts to prevent accidents, such as collisions, at an early stage. Since there was no multispectral pedestrian detection dataset in an intralogistics domain, we collected a dataset; the dataset employs a method that aligns image pairs with different domains, i.e. RGB and thermal, without the use of a cumbersome device such as a beam splitter, but rather by exploiting the disparity between RGB sensors and camera geometry. In addition, we propose a multispectral pedestrian detector called SSD 2.5D that can not only detect pedestrians but also estimate the distance between an automated forklift and workers. In extensive experiments, the performance of detection and centroid localization is validated with respect to evaluation metrics used in the driving car domain but with distinct categories, such as hazardous zone and warning zone, to make it more applicable to the intralogistics domain.

With the growth of the video streaming industry, video retrieval and video alignment are facing high levels of demand. Several studies have demonstrated the feasibility of these methods for various problems related to video retrieval and alignment independently, but test in a unified framework has never been done. However, in real-world applications, it is also concurrently necessary not only to find which video pairs are similar (video retrieval) but also to align the positions of the pair that are related (video alignment). In this paper, we present a new task that simultaneously retrieves and aligns videos. As a solution to this task, a simultaneous retrieval and alignment framework abbreviated as SRA is proposed, which is a two-stage approach consisting of a foreground proposal stage and a downstream stage to efficiently process untrimmed videos. Furthermore, two criteria are suggested to support the new task: a metric mAP@J assessing how highly the related videos are ranked and how well relevant positions are assigned in that video, and a dataset FIVR+A that includes video-level relationships and hierarchical segment-level annotations. Finally, we conduct multi-pronged analyses to assess how our approach handles the new task in various experiments.

Multispectral recognition has attracted increasing attention from the research community due to its potential competence for many applications from day to night. However, due to the domain shift between RGB and thermal image, it has still many challenges to apply and to use RGB domain-based tasks. To reduce the domain gap, we propose multispectral domain invariant framework, which leverages the unpaired image translation method to generate a semantic and strongly discriminative invariant image by enforcing novel constraints in the objective function. We demonstrate the efficacy of the proposed method on mainly multispectral place recognition task and achieve significant improvement compared to previous works. Furthermore, we test on multispectral semantic segmentation and unsupervised domain adaptations to prove the scalability and generality of the proposed method. We will open our source code and dataset.

Pedestrian detection has long been a prominent area of focus in computer vision due to its extensive applications, particularly in the development of autonomous driving systems. While color image-based pedestrian detection has achieved significant progress, its vulnerability to illumination changes has prompted more research into multispectral pedestrian detection, which leverages both visible and infrared modalities for robust detection in varying lighting conditions. Despite advances in multispectral detection models, research on applying self-supervised learning for feature representation in this area remains limited. In this study, we extend existing self-supervised learning approaches for color image data to multispectral pedestrian detection. By pre-training with self-supervised learning methods and fine-tuning, we evaluate their extensibility to the multispectral domain. Experimental results demonstrate that self-supervised learning enhances multispectral pedestrian detection, especially in nighttime conditions, outperforming models pretrained only on color modalities. Furthermore, we analyze the framework of self-supervised learning method that perform well on multispectral data, providing insights into which framework elements enhance multispectral pedestrian detection. This study underscores the potential of self-supervised learning in multispectral pedestrian detection and its role in advancing detection robustness for critical applications such as autonomous driving.