Design of Sports Image Contour Feature Acquisition System Based on the Background Subtraction Method

Moving target detection (MTD) is one of the emphases and difficulties in the field of computer vision and image processing. It is the basis of moving target tracking and behavior recognition. We propose two methods are improved and fused, respectively, and the fusion algorithm is applied to the complex scene for MTD, so as to improve the accuracy of MTD in complex and hybrid scenes. Using the main idea of the three-frame difference image method, the background difference method and the interframe difference method are combined to make their advantages complementary to overcome each other’s weaknesses. The experimental results show that the method can be well adapted to the situation of periodic motion interference in the background, and it can adapt to the situation of sudden background changes.

Aspects of the Language and Thought of Four-Year-Old Maori Children: a Study Based on Bierwisch's Componential Analysis of a Set of Adjectives

<p>Using an analysis developed by the linguist Manfred Bierwisch of the semantic components of the set of spatial adjectives, big, little, long, short, high, low, wide, narrow, deep, shallow, far, near, thick, thin, fat, thin, tall and short, four series of tests were constructed in order to determine whether differences existed in the meaning systems of Maori and of Pakeha four-year-old children with respect to these words, and whether Maori and Pakeha performances were similar across all four series. The series were: (a) A word recognition series testing for components of meaning in which pairs of components were placed in binary opposition. (b) An implication series testing for understanding of the concepts referred to by the words of the set. (c) An anomaly series, designed to elicit words of the set and to explore the children's understanding of the use of words. (d) A feature series which explored the children's implicit understanding of normativity and proportion. In addition the children were asked to do a drawing of something big and something little. Their mothers were also interviewed in order to collect information about a number of background variables such as mother's education, father's occupation and the language background of the child. Maori and Pakeha samples were established by asking the mothers to give the ethnic identity of the child. The main findings were that the Pakeha performed better than the Maori sample on recognition of the set of target words but this difference did not reach a level of statistical significance. Two words of the set, low and wide were recognised significantly more often by Pakeha than by Maori. With regard to the range of the words of the set elicited the Pakeha children produced a greater variety of words but, again, this difference was not statistically significant. The two samples performed about equally with regard to comprehension of the concepts signified by the words of the set. Nor was any important difference detected in the feature series or the drawings. An analysis of choice patterns showed no significant difference between the two samples. These results were interpreted to mean that the four-year-old Maori children in the sample did not exhibit cognitive deficit relative to the Pakehas even though they showed differences in word recognition and word use. Nor were they hampered in their access to the meaning of the words in the study by acquaintance with the Maori language. In order to assess the possible effects of various background factors, measures of word recognition, concepts, and strategies (choice patterns) were correlated with the background variables. The age of the child was significantly associated with the concept scores and with number of words elicited. Father's occupation was associated significantly with words recognised in the Pakeha sample but not in the Maori sample. In addition to exploring possible Maori-Pakeha differences in interpretation of words and concepts, the semantic feature acquisition hypothesis was examined and found to be inadequate as an explanation of the acquisition of words and meaning. An alternative multi-level model based on a hierarchy of preferred interpretations was developed to suggest the way in which the words of the set and their meanings are acquired by the young child.</p>

Aspects of the Language and Thought of Four-Year-Old Maori Children: a Study Based on Bierwisch's Componential Analysis of a Set of Adjectives

<p>Using an analysis developed by the linguist Manfred Bierwisch of the semantic components of the set of spatial adjectives, big, little, long, short, high, low, wide, narrow, deep, shallow, far, near, thick, thin, fat, thin, tall and short, four series of tests were constructed in order to determine whether differences existed in the meaning systems of Maori and of Pakeha four-year-old children with respect to these words, and whether Maori and Pakeha performances were similar across all four series. The series were: (a) A word recognition series testing for components of meaning in which pairs of components were placed in binary opposition. (b) An implication series testing for understanding of the concepts referred to by the words of the set. (c) An anomaly series, designed to elicit words of the set and to explore the children's understanding of the use of words. (d) A feature series which explored the children's implicit understanding of normativity and proportion. In addition the children were asked to do a drawing of something big and something little. Their mothers were also interviewed in order to collect information about a number of background variables such as mother's education, father's occupation and the language background of the child. Maori and Pakeha samples were established by asking the mothers to give the ethnic identity of the child. The main findings were that the Pakeha performed better than the Maori sample on recognition of the set of target words but this difference did not reach a level of statistical significance. Two words of the set, low and wide were recognised significantly more often by Pakeha than by Maori. With regard to the range of the words of the set elicited the Pakeha children produced a greater variety of words but, again, this difference was not statistically significant. The two samples performed about equally with regard to comprehension of the concepts signified by the words of the set. Nor was any important difference detected in the feature series or the drawings. An analysis of choice patterns showed no significant difference between the two samples. These results were interpreted to mean that the four-year-old Maori children in the sample did not exhibit cognitive deficit relative to the Pakehas even though they showed differences in word recognition and word use. Nor were they hampered in their access to the meaning of the words in the study by acquaintance with the Maori language. In order to assess the possible effects of various background factors, measures of word recognition, concepts, and strategies (choice patterns) were correlated with the background variables. The age of the child was significantly associated with the concept scores and with number of words elicited. Father's occupation was associated significantly with words recognised in the Pakeha sample but not in the Maori sample. In addition to exploring possible Maori-Pakeha differences in interpretation of words and concepts, the semantic feature acquisition hypothesis was examined and found to be inadequate as an explanation of the acquisition of words and meaning. An alternative multi-level model based on a hierarchy of preferred interpretations was developed to suggest the way in which the words of the set and their meanings are acquired by the young child.</p>

An Improved Character Recognition Framework for Containers Based on DETR Algorithm

An improved DETR (detection with transformers) object detection framework is proposed to realize accurate detection and recognition of characters on shipping containers. ResneSt is used as a backbone network with split attention to extract features of different dimensions by multi-channel weight convolution operation, thus increasing the overall feature acquisition ability of the backbone. In addition, multi-scale location encoding is introduced on the basis of the original sinusoidal position encoding model, improving the sensitivity of input position information for the transformer structure. Compared with the original DETR framework, our model has higher confidence regarding accurate detection, with detection accuracy being improved by 2.6%. In a test of character detection and recognition with a self-built dataset, the overall accuracy can reach 98.6%, which meets the requirements of logistics information identification acquisition.

End-to-End Training for Compound Expression Recognition

For a long time, expressions have been something that human beings are proud of. That is an essential difference between us and machines. With the development of computers, we are more eager to develop communication between humans and machines, especially communication with emotions. The emotional growth of computers is similar to the growth process of each of us, starting with a natural, intimate, and vivid interaction by observing and discerning emotions. Since the basic emotions, angry, disgusted, fearful, happy, neutral, sad and surprised are put forward, there are many researches based on basic emotions at present, but few on compound emotions. However, in real life, people’s emotions are complex. Single expressions cannot fully and accurately show people’s inner emotional changes, thus, exploration of compound expression recognition is very essential to daily life. In this paper, we recommend a scheme of combining spatial and frequency domain transform to implement end-to-end joint training based on model ensembling between models for appearance and geometric representations learning for the recognition of compound expressions in the wild. We are mainly devoted to digging the appearance and geometric information based on deep learning models. For appearance feature acquisition, we adopt the idea of transfer learning, introducing the ResNet50 model pretrained on VGGFace2 for face recognition to implement the fine-tuning process. Here, we try and compare two minds, one is that we utilize two static expression databases FER2013 and RAF Basic for basic emotion recognition to fine tune, the other is that we fine tune the model on the input three channels composed of images generated by DWT2 and WAVEDEC2 wavelet transforms based on rbio3.1 and sym1 wavelet bases respectively. For geometric feature acquisition, we firstly introduce a densesift operator to extract facial key points and their histogram descriptions. After that, we introduce deep SAE with a softmax function, stacked LSTM and Sequence-to-Sequence with stacked LSTM and define their structures by ourselves. Then, we feed the salient key points and their descriptions into three models to train respectively and compare their performances. When the model training for appearance and geometric features learning is completed, we combine the two models with category labels to achieve further end-to-end joint training, considering that ensembling models, which describe different information, can further improve recognition results. Finally, we validate the performance of our proposed framework on an RAF Compound database and achieve a recognition rate of 66.97%. Experiments show that integrating different models, which express different information, and achieving end-to-end training can quickly and effectively improve the performance of the recognition.

Active feature acquisition on data streams under feature drift

Traditional active learning tries to identify instances for which the acquisition of the label increases model performance under budget constraints. Less research has been devoted to the task of actively acquiring feature values, whereupon both the instance and the feature must be selected intelligently and even less to a scenario where the instances arrive in a stream with feature drift. We propose an active feature acquisition strategy for data streams with feature drift, as well as an active feature acquisition evaluation framework. We also implement a baseline that chooses features randomly and compare the random approach against eight different methods in a scenario where we can acquire at most one feature at the time per instance and where all features are considered to cost the same. Our initial experiments on 9 different data sets, with 7 different degrees of missing features and 8 different budgets show that our developed methods outperform the random acquisition on 7 data sets and have a comparable performance on the remaining two.

Target-oriented model-based seismic footprint analysis and mitigation

Compensating for the effects of an acquisition footprint can be one of the most daunting problems when using seismic attributes for quantitative interpretation. This is especially true for unconventional plays because they are on land with accompanying irregular acquisition geometries. Additionally, in such plays, the physical property changes are often small, making the seismic amplitude fidelity critical. We have developed a methodology that integrates a 1D elastic prestack synthetic model with 3D acquisition geometry to accurately model the seismic footprint produced by irregular or insufficient sampling of primary reflectivity. The stacked amplitude response of the modeled survey is then used to mitigate the poststack footprint on the field seismic. Modeling and removing this element of the acquisition footprint quantitatively improve the interpretive value of the mapped seismic amplitudes. In our study area, correlation between seismic amplitudes and well control increased from an [Formula: see text] of 0.053 before correction to an [Formula: see text] of 0.629 after. Our approach is especially effective in situations in which the spatial frequency of the footprint overlaps that of the geologic signal. Geological feature: Acquisition related seismic amplitude artifacts Seismic appearance: Smoothly varying amplitude changes Alternative interpretations: Bed thickness variation Features with similar appearance: Carbonate porosity Formation: Niobrara Formation, mixed chalks and marlstones Age: Upper Cretaceous Location: Wattenberg Field, Denver Basin, north central Colorado Seismic data: Joint acquisition between Anadarko Petroleum and Colorado School of Mines, Reservoir Characterization Project Analysis tools: Elastic prestack seismic modeling