In our study, the effects of water stress on photosynthesis and photosynthetic electron transport chain (PETC) were studied in several ways, including monitoring the change of gas exchange parameters, modulated chlorophyll fluorescence, rapid fluorescence induction kinetics, reactive oxygen species (ROS), antioxidant enzyme activities and D1 protein levels in apple leaves. Our results show that when leaf water potential (ψ_w) is above –1.5 MPa, the stomatal limitation should be the main reason for a drop of photosynthesis. In this period, photosynthetic rate (P_N), stomatal conductance (G_s), transpiration rate (E) and intercellular CO₂ concentration (C_i) all showed a strong positive correlation with ψ_w. Modulated chlorophyll fluorescence parameters related to photosynthetic biochemistry activity including maximum photochemical efficiency (F_v/F_m), actual photochemical efficiency of PSII (Φ_PSII), photochemical quenching coefficient (q_P) and coefficient of photochemical fluorescence quenching assuming interconnected PSII antennae (q_L) also showed a strong positive correlation as ψ_w gradually decreased. On the other hand, in this period, Stern-Volmer type non-photochemical quenching coefficient (NPQ) and quantum yield of light-induced non-photochemical fluorescence quenching [Y_(NPQ)] kept going up, which shows an attempt to dissipate excess energy to avoid damage to plants. When ψ_w was below –1.5 MPa, P_N continued to decrease linearly, while C_i increased and a ‘V’ model presents the correlation between C_i and ψ_w by polynomial regression. This implies that, in this period, the drop in photosynthesis activity might be caused by non-stomatal limitation. F_v/F_m, Φ_PSII, q_P and q_L in apple leaves treated with water stress were much lower than in control, while NPQ and Y_(NPQ) started to go down. This demonstrates that excess energy might exceed the tolerance ability of apple leaves. Consistent with changes of these parameters, excess energy led to an increase in the production of ROS including H₂O₂ and O₂•⁻. Although the activities of antioxidant enzymes like catalase (CAT), superoxide dismutase (SOD) and peroxidase (POD) increased dramatically and ascorbate peroxidase (APX) decreased in apple leaves with drought stress, it was still not sufficient to scavenge ROS. Consequently, the accumulation of ROS triggered a reduction of net D1 protein content, a core protein in the PSII reaction center. As D1 is responsible for the photosynthetic electron transport from plastoquinone A (Q_A) to plastoquinone B (Q_B), the capacity of PETC between Q_A and Q_B was considerably downregulated. The decline of photosynthesis and activity of PETC may result in the shortage of adenosine triphosphate (ATP) and limitation the regeneration of RuBP (J_max), a key enzyme in CO₂ assimilation. These are all non-stomatal factors and together contributed to decreased CO₂ assimilation under severe water stress.

Vehicles, pedestrians, and riders are the most important and interesting objects for the perception modules of self-driving vehicles and video surveillance. However, the state-of-the-art performance of detecting such important objects (esp. small objects) is far from satisfying the demand of practical systems. Large-scale, rich-diversity, and high-resolution datasets play an important role in developing better object detection methods to satisfy the demand. Existing public large-scale datasets such as MS COCO collected from websites do not focus on the specific scenarios. Moreover, the popular datasets (e.g., KITTI and Citypersons) collected from the specific scenarios are limited in the number of images and instances, the resolution, and the diversity. To attempt to solve the problem, we build a diverse high-resolution dataset (called TJU-DHD). The dataset contains 115,354 high-resolution images (52% images have a resolution of 1624×1200 pixels and 48% images have a resolution of at least 2,560×1,440 pixels) and 709,330 labeled objects in total with a large variance in scale and appearance. Meanwhile, the dataset has a rich diversity in season variance, illumination variance, and weather variance. In addition, a new diverse pedestrian dataset is further built. With the four different detectors (i.e., the one-stage RetinaNet, anchor-free FCOS, two-stage FPN, and Cascade R-CNN), experiments about object detection and pedestrian detection are conducted. We hope that the newly built dataset can help promote the research on object detection and pedestrian detection in these two scenes. The dataset is available at https://github.com/tjubiit/TJU-DHD.

Remote sensing image dehazing is a well-known remote sensing image processing task focused on restoring clean images from hazy images. The Transformer network, based on the self-attention mechanism, has demonstrated remarkable advantages in various image restoration tasks, due to its capacity to capture long-range dependencies within images. However, it is weak at modeling local context. Conversely, convolutional neural networks (CNNs) are adept at capturing local contextual information. Local contextual information could provide more details, while long-range dependencies capture global structure information. The combination of long-range dependencies and local context modeling is beneficial for remote sensing image dehazing. Therefore, in this paper, we propose a CNN-based adaptive local context enrichment module (ALCEM) to extract contextual information within local regions. Subsequently, we integrate our proposed ALCEM into the multi-head self-attention and feed-forward network of the Transformer, constructing a novel locally enhanced attention (LEA) and a local continuous-enhancement feed-forward network (LCFN). The LEA utilizes the ALCEM to inject local context information that is complementary to the long-range relationship modeled by multi-head self-attention, which is beneficial to removing haze and restoring details. The LCFN extracts multi-scale spatial information and selectively fuses them by the the ALCEM, which supplements more informative information compared with existing regular feed-forward networks with only position-specific information flow. Powered by the LEA and LCFN, a novel Transformer-based dehazing network termed LCEFormer is proposed to restore clear images from hazy remote sensing images, which combines the advantages of CNN and Transformer. Experiments conducted on three distinct datasets, namely DHID, ERICE, and RSID, demonstrate that our proposed LCEFormer achieves the state-of-the-art performance in hazy scenes. Specifically, our LCEFormer outperforms DCIL by 0.78 dB and 0.018 for PSNR and SSIM on the DHID dataset.

Transformers have shown promising progress in various visual object detection tasks, including monocular 2D/3D detection and surround-view 3D detection. More importantly, the attention mechanism in the Transformer model and the 3D information extraction in binocular stereo are both similarity-based. However, directly applying existing Transformer-based detectors to binocular stereo 3D object detection leads to slow convergence and significant precision drops. We argue that a key cause of that defect is that existing Transformers ignore the binocular-stereo-specific image correspondence information. In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information. To achieve this goal, we present TS3D, a Transformer-based Stereo-aware 3D object detector. In the TS3D, a Disparity-Aware Positional Encoding (DAPE) module is proposed to embed the image correspondence information into stereo features. The correspondence is encoded as normalized sub-pixel-level disparity and is used in conjunction with sinusoidal 2D positional encoding to provide the 3D location information of the scene. To enrich multi-scale stereo features, we propose a Stereo Preserving Feature Pyramid Network (SPFPN). The SPFPN is designed to preserve the correspondence information while fusing intra-scale and aggregating cross-scale stereo features. Our proposed TS3D achieves a 41.29% Moderate Car detection average precision on the KITTI test set and takes 88 ms to detect objects from each binocular image pair. It is competitive with advanced counterparts in terms of both precision and inference speed.