Intelligent System for Estimation of the Spatial Position of Apples Based on YOLOv3 and Real Sense Depth Camera D415

Despite the great possibilities of modern neural network architectures concerning the problems of object detection and recognition, the output of such models is the local (pixel) coordinates of objects bounding boxes in the image and their predicted classes. However, in several practical tasks, it is necessary to obtain more complete information about the object from the image. In particular, for robotic apple picking, it is necessary to clearly understand where and how much to move the grabber. To determine the real position of the apple relative to the source of image registration, it is proposed to use the Intel Real Sense depth camera and aggregate information from its depth and brightness channels. The apples detection is carried out using the YOLOv3 architecture; then, based on the distance to the object and its localization in the image, the relative distances are calculated for all coordinates. In this case, to determine the coordinates of apples, a transition to a symmetric coordinate system takes place by means of simple linear transformations. Estimating the position in a symmetric coordinate system allows estimating not only the magnitude of the shift but also the location of the object relative to the camera. The proposed approach makes it possible to obtain position estimates with high accuracy. The approximate root mean square error is 7–12 mm, depending on the range and axis. As for precision and recall metrics, the first is 100% and the second is 90%.

DEICTIC PRONOUNS IN THE KHAKASS LANGUAGE

В настоящей статье представлены результаты исследования дейктических (указательных) местоимений в хакасском языке. Дейктические местоимения, как и другие указательные слова, выступают в качестве слов, служащих для определения степени удаленности объекта относительно позиции говорящего лица («дейктического центра»). В каждом языке своя (двучленная, трехчленная и более) система определения степени удаленности предмета относительно дейктического центра. В хакасском языке степень удаленности предметов относительно говорящего лица определяется через трехчленную систему: проксимальную («ближе к говорящему лицу»), медиальную («чуть дальше от говорящего лица») и экстремальную («далеко от говорящего лица»). Кроме того, дейктические местоимения служат для развития темпорального значения. В предложении дейктическим местоимениям отводится роль определения и обстоятельства времени. This article presents the results of a study of deictic (demonstrative) pronouns in the Khakass language. Deictic pronouns, like other demonstrative words, act as words that serve to determine the degree of remoteness of the object relative to the position of the speaker ("deictic center"). Each language has its own (binomial, three-term, and more) system for determining the degree of remoteness of the subject relative to the deictic center. In the Khakass language, the degree of remoteness of objects relative to the speaking person is determined through a three-term system: proximal ("closer to the speaking person"), medial ("slightly further from the speaking person") and extreme ("far from the speaking person"). In addition, deictic pronouns serve to develop a temporal meaning. In the sentence, the deictic pronouns are assigned the role of the definition and the circumstance of time.

Similarity-based interference and relative clauses in second language processing

Relative clauses have long been examined in research on first (L1) and second (L2) language acquisition and processing, and a large body of research has shown that object relative clauses (e.g. ‘The boy that the girl saw’) are more difficult to process than subject relative clauses (e.g. ‘The boy that saw the girl’). Although there are different accounts of this finding, memory-based factors have been argued to play a role in explaining the object relative disadvantage. Evidence of memory-based factors in relative clause processing comes from studies indicating that representational similarity influences the difficulty associated with object relatives as a result of a phenomenon known as similarity-based interference. Although similarity-based interference has been well studied in L1 processing, less is known about how it influences L2 processing. We report two studies – an eye-tracking experiment and a comprehension task – investigating interference in the comprehension of relative clauses in L1 and L2 readers. Our results indicated similarity-based interference in the processing of object relative clauses in both L1 and L2 readers, with no significant differences in the size of interference effects between the two groups. These results highlight the importance of considering memory-based factors when examining L2 processing.

ACTUAL PARTICLES OF THE KARATIN LANGUAGE INDICATING THE DISTANCE OF THE OBJECT

The article examines the deictic particles of the Karatin language, indicating the localization of the object relative to the speaker away from it horizontally and vertically. There is an increase in deictic semantics in the joint use of particles and the corresponding demonstrative pronouns or pronominal adverbs.

Comprehension of Complex Structures by Persian-speaking Aphasics: The Role of Cognitive Load

Introduction: So far, many studies have investigated the extent and nature of the grammatical deficit in aphasia. However, to the best of our knowledge, this research is the first in the Persian language to inspect the comprehension of patients with Broca’s aphasia on diverse syntactically complex structures. Materials and Methods: To scrutinize the impact of task on aphasics’ performance, four age-, education- and gender-matched Persian-speaking patients with Broca’s aphasia were compared with their healthy matched controls regarding the two different tasks of grammatical judgment and figurine act-out task. The structures used to examine the subjects’ performance included agentive passive, subject cleft, object cleft, object relative clause, and object experiencer psychological verbs. Results: Our results which supported the trade-off hypothesis, showed that our subjects generally performed better in grammatical judgment task than in figurine act-out task (P≤0.05). Particularly in the second task, as our inner task comparison, the patients’ problems were more severe in object cleft, object experiencer, and object relative clauses: all structures whose interpretations need more cognitive load. Conclusion: Our findings put more weight on the interactive or constraint-based model of language processing.

The structure of the local detector of the reprint model of the object in the image

Currently, methods for recognizing objects in images work poorly and use intellectually unsatisfactory methods. The existing identification systems and methods do not completely solve the problem of identification, namely, identification in difficult conditions: interference, lighting, various changes on the face, etc. To solve these problems, a local detector for a reprint model of an object in an image was developed and described. A transforming autocoder (TA), a model of a neural network, was developed for the local detector. This neural network model is a subspecies of the general class of neural networks of reduced dimension. The local detector is able, in addition to determining the modified object, to determine the original shape of the object as well. A special feature of TA is the representation of image sections in a compact form and the evaluation of the parameters of the affine transformation. The transforming autocoder is a heterogeneous network (HS) consisting of a set of networks of smaller dimension. These networks are called capsules. Artificial neural networks should use local capsules that perform some rather complex internal calculations on their inputs, and then encapsulate the results of these calculations in a small vector of highly informative outputs. Each capsule learns to recognize an implicitly defined visual object in a limited area of viewing conditions and deformations. It outputs both the probability that the object is present in its limited area and a set of “instance parameters” that can include the exact pose, lighting, and deformation of the visual object relative to an implicitly defined canonical version of this object. The main advantage of capsules that output instance parameters is a simple way to recognize entire objects by recognizing their parts. The capsule can learn to display the pose of its visual object in a vector that is linearly related to the “natural” representations of the pose that are used in computer graphics. There is a simple and highly selective test for whether visual objects represented by two active capsules A and B have the correct spatial relationships for activating a higher-level capsule C. The transforming autoencoder solves the problem of identifying facial images in conditions of interference (noise), changes in illumination and angle.

Locality in the acquisition of object A’-dependencies: insights from French

Children’s difficulties with dependencies involving movement of an object to the left periphery of the clause (object relative clauses/RCs and wh-questions), have been explained in terms of intervention effects arising when the moved object and the intervening subject share a lexical N feature (Friedmann, Belletti & Rizzi 2009). Such an account raises various questions: (1) Do these effects hold in the absence of a lexical N feature when the object and the intervener share other relevant features? (2) Do phi-features with a semantic role modulate such effects? (3) Does the degree of feature overlap determine a gradience in performance? We addressed these in three sentence-picture matching studies with French-speaking children (4;8 to 6;3), by assessing comprehension of (1) subject and object RCs headed by the demonstrative pronouns celui/celle and matching or mismatching in number; (2) object RCs headed by a lexical N and matching or mismatching in animacy; (3) object who- and which-questions. Our results show that mismatches in number, not in animacy, enhance comprehension of object RCs, even in the absence of a lexical N feature, and confirm previous findings that object who-questions yield better comprehension than object which-questions. Comparing across studies, the following gradation emerges with respect to performance accuracy: disjunction > intersection > inclusion. The global interpretation of these findings is that fine-grained phi-features determining movement are both sufficient and necessary for locality, and the degree of overlap of these features can capture the pattern of performance observed in children, namely higher accuracy as featural differences increase.

Two types of alignment change in nominalizations

This paper investigates two instances of alignment change, both of which resulted from reanalysis of a nominalized embedded clause type, in which the external argument was marked with genitive case and the internal argument was focused. We show that a subject marked with genitive case in the early development of Austronesian languages became ergative-marked when object relative clauses in cleft constructions were reanalyzed as transitive root clauses. In contrast to this, the genitive case in Old Japanese nominalized clauses, marking an external argument, was extended to mark all subjects. This occurred after adnominal clauses were reanalyzed as root clauses. Japanese underwent one more step in order for genitive to be reanalyzed as nominative: the reanalysis of impersonal psych transitive constructions as intransitives. With these two case studies of Austronesian and Japanese, we show that reanalysis of nominalization goes in either direction, ergative or accusative, depending on the syntactic conditions involved in the reanalysis.

Comprehension and Eye Movements in the Processing of Subject- and Object-Relative Clauses: Evidence from Dyslexia and Individual Differences

In this study, we examined eye movements and comprehension in sentences containing a relative clause. To date, few studies have focused on syntactic processing in dyslexia and so one goal of the study is to contribute to this gap in the experimental literature. A second goal is to contribute to theoretical psycholinguistic debate concerning the cause and the location of the processing difficulty associated with object-relative clauses. We compared dyslexic readers (n = 50) to a group of non-dyslexic controls (n = 50). We also assessed two key individual differences variables (working memory and verbal intelligence), which have been theorised to impact reading times and comprehension of subject- and object-relative clauses. The results showed that dyslexics and controls had similar comprehension accuracy. However, reading times showed participants with dyslexia spent significantly longer reading the sentences compared to controls (i.e., a main effect of dyslexia). In general, sentence type did not interact with dyslexia status. With respect to individual differences and the theoretical debate, we found that processing difficulty between the subject and object relatives was no longer significant when individual differences in working memory were controlled. Thus, our findings support theories, which assume that working memory demands are responsible for the processing difficulty incurred by (1) individuals with dyslexia and (2) object-relative clauses as compared to subject relative clauses.

Paradoxical stabilization of relative position in moving frames

To capture where things are and what they are doing, the visual system may extract the position and motion of each object relative to its surrounding frame of reference [K. Duncker, Routledge and Kegan Paul, London 161–172 (1929) and G. Johansson, Acta Psychol (Amst.) 7, 25–79 (1950)]. Here we report a particularly powerful example where a paradoxical stabilization is produced by a moving frame. We first take a frame that moves left and right and we flash its right edge before, and its left edge after, the frame’s motion. For all frame displacements tested, the two edges are perceived as stabilized, with the left edge on the left and right edge on the right, separated by the frame’s width as if the frame were not moving. This stabilization is paradoxical because the motion of the frame itself remains visible, albeit much reduced. A second experiment demonstrated that unlike other motion-induced position shifts (e.g., flash lag, flash grab, flash drag, or Fröhlich), the illusory shift here is independent of speed and is set instead by the distance of the frame’s travel. In this experiment, two probes are flashed inside the frame at the same physical location before and after the frame moves. Despite being physically superimposed, the probes are perceived widely separated, again as if they were seen in the frame’s coordinates and the frame were stationary. This paradoxical stabilization suggests a link to visual stability across eye movements where the displacement of the entire visual scene may act as a frame to stabilize the perception of relative locations.