RESUMEN

Significant progress has been achieved in multi-object tracking (MOT) through the evolution of detection and re-identification (ReID) techniques. Despite these advancements, accurately tracking objects in scenarios with homogeneous appearance and heterogeneous motion remains a challenge. This challenge arises from two main factors: the insufficient discriminability of ReID features and the predominant utilization of linear motion models in MOT. In this context, we introduce a novel motion-based tracker, MotionTrack, centered around a learnable motion predictor that relies solely on object trajectory information. This predictor comprehensively integrates two levels of granularity in motion features to enhance the modeling of temporal dynamics and facilitate precise future motion prediction for individual objects. Specifically, the proposed approach adopts a self-attention mechanism to capture token-level information and a Dynamic MLP layer to model channel-level features. MotionTrack is a simple, online tracking approach. Our experimental results demonstrate that MotionTrack yields state-of-the-art performance on datasets such as Dancetrack and SportsMOT, characterized by highly complex object motion.

Asunto(s)

RESUMEN

Recently, advances in detection and re-identification techniques have significantly boosted tracking-by-detection-based multi-pedestrian tracking (MPT) methods and made MPT a great success in most easy scenes. Several very recent works point out that the two-step scheme of first detection and then tracking is problematic and propose using the bounding box regression head of an object detector to realize data association. In this tracking-by-regression paradigm, the regressor directly predicts each pedestrian's location in the current frame according to its previous position. However, when the scene is crowded and pedestrians are close to each other, the small and partially occluded targets are easily missed. In this paper, we follow this pattern and design a hierarchical association strategy to obtain better performance in crowded scenes. To be specific, at the first association, the regressor is used to estimate the positions of obvious pedestrians. At the second association, we employ a history-aware mask to filter out the already occupied regions implicitly and look carefully at the remaining regions to find out the ignored pedestrians during the first association. We integrate the hierarchical association in a learning framework and directly infer the occluded and small pedestrians in an end-to-end way. We conduct extensive pedestrian tracking experiments on three public pedestrian tracking benchmarks from less crowded to crowded scenes, demonstrating the proposed strategy's effectiveness in crowded scenes.

RESUMEN

The present study was conducted to reveal the effect of bags with different colors on the fruit coloration of 'Yunhongli No. 2'. The differences in fruit skin color, chlorophyll, flavonoids, total phenol, anthocyanin contents and the activities of related enzymes involved in anthocyanin synthesis among different bagging treatments were evaluated. The results showed that dark treatment at the fruit development stage was beneficial to skin coloration after bag removing. After removing bags, the anthocyanin content in the treatment of natural light was highest and the red coloration of the fruit skin were best, followed by the treatment of white bags. The different bagging treatments significantly affected the contents of chlorophyll, flavonoids, total phenol, anthocyanin in the fruit skin, thereby affected the skin coloration. The activities of related enzymes for anthocyanin synthesis showed significant differences among the different bagging treatments. The correlation analysis suggested that the anthocyanin content was significantly positively related with the activities of dihydroflavonol 4-reductase (DFR) and UDP-glucose flavonoid-3-O-glucosyltransf-erase (UFGT), however, it had no significant correlation with the activity of phenylalanin ammo-nialyase (PAL).

Asunto(s)