We present a cheap, lightweight, and fast fruit counting pipeline. Our pipeline relies only on a monocular camera, and achieves counting performance comparable to a state-of-the-art fruit counting system that utilizes an expensive sensor suite including a monocular camera, LiDAR and GPS/INS on a mango dataset. Our pipeline begins with a fruit and tree trunk detection component that uses state-of-the-art convolutional neural networks (CNNs). It then tracks fruits and tree trunks across images, with a Kalman Filter fusing measurements from the CNN detectors and an optical flow estimator. Finally, fruit count and map are estimated by an efficient fruit-as-feature semantic structure from motion (SfM) algorithm which converts 2D tracks of fruits and trunks into 3D landmarks, and uses these landmarks to identify double counting scenarios. There are many benefits of developing such a low cost and lightweight fruit counting system, including applicability to agriculture in developing countries, where monetary constraints or unstructured environments necessitate cheaper hardware solutions.Index Terms-Robotics in agriculture and forestry, deep learning in robotics and automation, visual tracking, mapping, object detection, segmentation and categorization.

No abstract

Ulcerative colitis (UC) is a chronic inflammatory bowel disease impacting patients’ quality of life and imposing heavy societal and economic burdens. Apoptosis of intestinal epithelial cells (IECs) has been considered an early event during the onset of UC and plays a crucial role in disease development. Thus, effectively inhibiting apoptosis of IECs is of critical significance for the clinical management of UC, presenting a potential direction for the research and development of pharmacotherapeutic agents. In recent years, research on the ameliorative effects of natural products on UC through inhibiting IECs apoptosis has attracted increasing attention and made remarkable achievements in ameliorating UC. In this review, we summarized the currently available research about the anti-apoptotic effects of natural products on UC and its mechanisms involving the death-receptor mediated pathway, mitochondrial-dependent pathway, ERS-mediated pathway, MAPK-mediated pathway, NF-κB mediated pathway, P13k/Akt pathway, JAK/STAT3 pathway, and NLRP3/ASC/Caspase-1 pathway. Hopefully, this review may yield useful information about the anti-apoptotic effects of natural products on UC and their potential molecular mechanisms and provide helpful insights for further investigations.

Chemical design and physical control of the molecular aggregation of organic semiconductors have been demonstrated to be efficient strategies to prepare high performance organic solar cells (OSCs). Starting from the non-fullerene acceptor (NFA) BTP-4Cl-C9-12, two NFAs named BTP-4Cl-C9-16 and BTP-4Cl-C9-20 with the alkyl chains of 2-ethylhexyl and 2octyldodecyl attached on the pyrrole rings are synthesized in this work. Through molecular dynamics simulations and experimental characterizations, we show that favorable three-dimensional (3D) honeycomb networks, which are beneficial for charge transport, can be formed in NFAs with the moderate alkyl chain length (BTP-4Cl-C9-12 and BTP-4Cl-C9-16), while two-dimensional honeycomb networks form in BTP-4Cl-C9-20 with long alkyl chains. 1,8-Diiodooctane solvent molecules adsorb on all alkyl chains of NFAs, reducing the adsorption energy between NFAs to promote their intermolecular interactions, especially in NFAs with longer alkyl chains. As a result, the synergistic effect of the 3D network and the appropriate domain size leads to a promising power conversion efficiency of 18.0% and 15.9% in thin-(100 nm) and thick-(300 nm) PM6:BTP-4Cl-C9-16 binary OSCs. This work presents a comprehensive understanding of the interaction between the NFA and solvent additive and provides rational guidance for the molecular design and morphology regulation of NFA-based OSCs toward higher performance.

No abstract