TWI811043B - Image processing system and image object superimposition apparatus and method thereof - Google Patents
Image processing system and image object superimposition apparatus and method thereof Download PDFInfo
- Publication number
- TWI811043B TWI811043B TW111128435A TW111128435A TWI811043B TW I811043 B TWI811043 B TW I811043B TW 111128435 A TW111128435 A TW 111128435A TW 111128435 A TW111128435 A TW 111128435A TW I811043 B TWI811043 B TW I811043B
- Authority
- TW
- Taiwan
- Prior art keywords
- image
- overlay
- frames
- original image
- objects
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 4
- 238000009877 rendering Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Landscapes
- Studio Circuits (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
Description
本發明是關於影像物件疊加技術,尤其是關於一種影像處理系統及其影像物件疊加裝置及方法。The present invention relates to image object overlay technology, in particular to an image processing system and its image object overlay device and method.
在現代人類的生活中,影像擷取裝置被大量地使用。舉例而言,可拍攝影片的手機或是長時間進行影像錄製的監控系統均會採用影像擷取裝置。其中,物件辨識是影像擷取裝置所衍生的重要技術,並可用以對特定的物件例如人臉、車牌等進行辨識。In modern human life, image capture devices are widely used. For example, mobile phones that can shoot videos or surveillance systems that record images for a long time will use image capture devices. Among them, object recognition is an important technology derived from image capture devices, and can be used to recognize specific objects such as human faces and license plates.
以往在物件辨識後,影像處理的裝置往往會對所有的物件設置一個大的圖框來涵蓋所有的物件,以標示具有物件的範圍並進行儲存。然而這樣的處理方式在物件分散時,將使過多沒有物件的影像範圍也被儲存,造成記憶體的浪費。並且,單一圖框的形式並無法針對個別物件進行不同的設定,在顯示上的運用彈性不足。In the past, after object recognition, image processing devices usually set a large frame to cover all objects, so as to mark and store the range with objects. However, when objects are dispersed in such a processing method, too many image ranges without objects will be stored, resulting in a waste of memory. Moreover, the form of a single frame cannot be set differently for individual objects, and the flexibility of display is insufficient.
鑑於先前技術的問題,本發明之一目的在於提供一種影像處理系統及其影像物件疊加裝置及方法,以改善先前技術。In view of the problems in the prior art, an object of the present invention is to provide an image processing system and an image object overlay device and method therefor, so as to improve the prior art.
本發明包含一種影像物件疊加裝置,包含:物件辨識電路、圖形繪製電路、圖形處理電路以及疊加電路。物件辨識電路配置以對原始影像包含的複數物件進行辨識以產生物件辨識資訊。圖形繪製電路配置以根據物件辨識資訊繪製複數物件圖框以儲存至記憶體,其中物件圖框分別對應物件,且物件圖框使用記憶體的空間總和小於原始影像的資料大小。圖形處理電路包含複數圖形處理單元電路,圖形處理單元電路對物件圖框進行處理以產生複數處理後物件圖框。疊加電路配置以將處理後物件圖框疊加於原始影像上,進而輸出合成影像。The invention includes an image object overlay device, which includes: an object identification circuit, a graphics drawing circuit, a graphics processing circuit and a superposition circuit. The object identification circuit is configured to identify multiple objects included in the original image to generate object identification information. The graphics drawing circuit is configured to draw a plurality of object frames according to the object identification information and store them in the memory, wherein the object frames respectively correspond to the objects, and the total memory space used by the object frames is smaller than the data size of the original image. The graphics processing circuit includes a plurality of graphics processing unit circuits, and the graphics processing unit circuits process object frames to generate a plurality of processed object frames. The overlay circuit is configured to overlay the processed object frame on the original image, and then output a composite image.
本發明另包含一種影像物件疊加方法,應用於影像物件疊加裝置中,包含:由物件辨識電路對原始影像包含的複數物件進行辨識以產生物件辨識資訊;由圖形繪製電路根據物件辨識資訊繪製複數物件圖框以儲存至記憶體,其中物件圖框分別對應物件,且物件圖框使用記憶體的空間總和小於原始影像的資料大小;由圖形處理電路包含的複數圖形處理單元電路對物件圖框進行處理以產生複數處理後物件圖框;以及由疊加電路將處理後物件圖框疊加於原始影像上,進而輸出合成影像。The present invention also includes a method for overlaying image objects, which is applied to an image object overlay device, comprising: an object identification circuit identifies a plurality of objects included in the original image to generate object identification information; a graphics drawing circuit draws the plurality of objects according to the object identification information The frame is stored in the memory, wherein the object frame corresponds to the object respectively, and the total space of the memory used by the object frame is smaller than the data size of the original image; the plurality of graphics processing unit circuits included in the graphics processing circuit process the object frame to generate a plurality of processed object frames; and the superimposed circuit superimposes the processed object frames on the original image, and then outputs a synthetic image.
本發明更包含一種影像處理系統,包含:影像擷取裝置、記憶體、影像物件疊加裝置以及顯示裝置。影像擷取裝置配置以進行影像擷取,產生原始影像。影像物件疊加裝置包含:物件辨識電路、圖形繪製電路、圖形處理電路以及疊加電路。物件辨識電路配置以接收原始影像,並對原始影像包含的複數物件進行辨識以產生物件辨識資訊。圖形繪製電路配置以根據物件辨識資訊繪製複數物件圖框以儲存至記憶體,其中物件圖框分別對應物件,且物件圖框使用記憶體的空間總和小於原始影像的資料大小。圖形處理電路包含複數圖形處理單元電路,圖形處理單元電路對物件圖框進行處理以產生複數處理後物件圖框。疊加電路配置以將處理後物件圖框疊加於原始影像上,進而輸出合成影像。顯示裝置配置以接收並顯示合成影像。The present invention further includes an image processing system, including: an image capture device, a memory, an image object overlay device and a display device. The image capture device is configured to capture images to generate original images. The image object overlay device includes: an object identification circuit, a graphics drawing circuit, a graphics processing circuit and a superposition circuit. The object identification circuit is configured to receive the original image, and identify multiple objects included in the original image to generate object identification information. The graphics drawing circuit is configured to draw a plurality of object frames according to the object identification information and store them in the memory, wherein the object frames respectively correspond to the objects, and the total memory space used by the object frames is smaller than the data size of the original image. The graphics processing circuit includes a plurality of graphics processing unit circuits, and the graphics processing unit circuits process object frames to generate a plurality of processed object frames. The overlay circuit is configured to overlay the processed object frame on the original image, and then output a composite image. The display device is configured to receive and display the composite image.
有關本案的特徵、實作與功效,茲配合圖式作較佳實施例詳細說明如下。About the feature, implementation and effect of this case, hereby cooperate with drawing as preferred embodiment and describe in detail as follows.
本發明之一目的在於提供一種影像處理系統及其影像物件疊加裝置及方法,針對個別物件進行辨識並繪製物件圖框,不僅大幅降低記憶體的使用量,更可依需求而對物件圖框進行不同的處理,達到具有彈性的顯示效果。An object of the present invention is to provide an image processing system and its image object overlay device and method, which can identify individual objects and draw object frames, which not only greatly reduces the amount of memory used, but also allows object frames to be processed according to requirements. Different processing to achieve flexible display effect.
請參照圖1。圖1顯示本發明一實施例中,一種影像處理系統100的方塊圖。影像處理系統100包含:影像擷取裝置110、記憶體120、影像物件疊加裝置130以及顯示裝置140。Please refer to Figure 1. FIG. 1 shows a block diagram of an
影像擷取裝置110可包含一種或多種感光元件,並配置以進行影像擷取,產生原始影像OI。The
影像物件疊加裝置130配置以接收原始影像OI進行物件辨識,據以繪製相應的物件圖框並疊加於原始影像OI上,產生合成影像SI。於一實施例中,除物件疊加外,影像物件疊加裝置130亦可選擇性進行例如,但不限於自動對焦、自動曝光、自動白平衡、高動態範圍成像(high dynamic range imaging;HDRI)、降噪或其組合的處理來產生合成影像SI。The image object
顯示裝置140配置以接收並顯示合成影像SI。The
在不同的應用中,影像處理系統100可為影像監控系統、影像擷取系統或其他可擷取影像進行處理與顯示的電子系統。其中,原始影像OI可為一個原始影像串流中的一張影像,合成影像SI亦可為一個合成影像串流中的一張影像。藉由影像物件疊加裝置130的處理,合成影像SI可在不影響原始影像OI的情形下,包含對應於不同物件的物件圖框,以便於後續的資料處理。In different applications, the
以下將針對影像物件疊加裝置130的結構與運作方式進行更詳細的說明。The structure and operation of the image object
請同時參照圖2以及圖3。圖2顯示本發明一實施例中,記憶體120以及影像物件疊加裝置130的方塊圖。圖3顯示本發明一實施例中,原始影像OI的示意圖。Please refer to Figure 2 and Figure 3 at the same time. FIG. 2 shows a block diagram of the
如圖2所示,影像物件疊加裝置130包含:處理器200、物件辨識電路210、圖形繪製電路220、圖形處理電路230、疊加電路240以及記憶體介面電路250。As shown in FIG. 2 , the image object
處理器200配置以運作資源配置軟體RGN,以對各電路進行設定與控制。The
物件辨識電路210配置以接收原始影像OI,並對原始影像OI包含的複數物件進行辨識以產生物件辨識資訊ODI。The
如圖3所示,原始影像OI中包含六個物件OB1~OB6。在圖3中,物件OB1~OB6是以人臉為範例,然而在其他實施例中亦可為例如但不限於車牌或其他可依實際需求處理要進行辨識的物體。As shown in FIG. 3 , the original image OI includes six objects OB1 - OB6 . In FIG. 3 , the objects OB1 - OB6 are human faces as an example, but in other embodiments, they can also be, for example but not limited to, license plates or other objects that can be processed and recognized according to actual needs.
於一實施例中,物件辨識資訊ODI可為包含但不限於各物件OB1~OB6在原始影像OI中的遠近資訊。於一實施例中,當物件均為同一屬性的物件(例如均為人臉)時,遠近資訊可由物件的尺寸大小決定。舉例而言,當物件的尺寸愈大,可判斷為具有相對較近位置。而當物件的尺寸愈小,可判斷為具有相對較遠位置。In one embodiment, the object identification information ODI may include but not limited to distance information of each object OB1 - OB6 in the original image OI. In one embodiment, when the objects are all of the same attribute (for example, both are human faces), the distance information can be determined by the size of the objects. For example, when the size of the object is larger, it can be determined that it has a relatively closer position. And when the size of the object is smaller, it can be judged to have a relatively far position.
須注意的是,上述資訊的定義以及獲取方式僅為一範例。本發明並不限於此。It should be noted that the definition and acquisition method of the above information is just an example. The present invention is not limited thereto.
記憶體120配置以儲存資料,並可由處理器200、物件辨識電路210、圖形繪製電路220、圖形處理電路230以及疊加電路240進行存取。於一實施例中,記憶體120為例如,但不限於動態隨機存取記憶體(dynamic random access memory;DRAM),且此些電路可藉由記憶體介面電路250對記憶體120進行存取。The
記憶體120包含原始影像儲存區塊IB以及複數物件儲存區塊BB1~BB6。原始影像儲存區塊IB配置以儲存原始影像OI。於一實施例中,物件辨識電路210可在接收到原始影像OI後,將原始影像OI儲存於原始影像儲存區塊IB中。The
圖形繪製電路220接收物件辨識資訊ODI並據以運作。於一實施例中,物件辨識資訊ODI可選擇性的由處理器200運作的資源配置軟體RGN傳送至圖形繪製電路220,或是直接由物件辨識電路210傳送至圖形繪製電路220。The
圖形繪製電路220配置以根據物件辨識資訊ODI繪製複數物件圖框OF1~OF6以儲存至記憶體120之物件儲存區塊BB1~BB6中。The
請同時參照圖4。圖4顯示本發明一實施例中,物件圖框OF1~OF6的示意圖。Please also refer to Figure 4. FIG. 4 shows a schematic diagram of object frames OF1-OF6 in an embodiment of the present invention.
如圖4所示,物件圖框OF1~OF6分別對應圖3中的物件OB1~OB6,且物件圖框OF1~OF6以實線繪製的邊框分別對應於圖3中以虛線表示的物件範圍。於一實施例中,圖形繪製電路220為具有繪圖引擎的電路,並配置以根據物件辨識資訊ODI繪出物件圖框OF1~OF6。As shown in FIG. 4 , the object frames OF1-OF6 respectively correspond to the objects OB1-OB6 in FIG. 3 , and the borders drawn by solid lines in the object frames OF1-OF6 respectively correspond to the ranges of objects indicated by dotted lines in FIG. 3 . In one embodiment, the
於一實施例中,物件圖框OF1~OF6與物件儲存區塊BB1~BB6的對應關係可由資源配置軟體RGN根據物件辨識資訊ODI設定。更詳細的說,資源配置軟體RGN在接收物件辨識資訊ODI後,可得知物件OB1~OB6的數目、座標以及尺寸大小。In one embodiment, the corresponding relationship between the object frames OF1-OF6 and the object storage blocks BB1-BB6 can be set by the resource configuration software RGN according to the object identification information ODI. More specifically, after receiving the object identification information ODI, the resource allocation software RGN can know the number, coordinates and sizes of the objects OB1-OB6.
資源配置軟體RGN將進而向記憶體120要求相應的物件儲存區塊BB1~BB6,其中此些物件儲存區塊BB1~BB6具有可將物件圖框OF1~OF6進行儲存的數目與尺寸大小。資源配置軟體RGN可記錄物件儲存區塊BB1~BB6的尺寸大小以及位址。其中,物件圖框OF1~OF6使用記憶體120的空間總和小於原始影像OI的資料大小。The resource allocation software RGN will then request the corresponding object storage blocks BB1-BB6 from the
圖形處理電路230包含複數圖形處理單元電路PD1~PD6,分別對物件圖框OF1~OF6進行處理以產生複數處理後物件圖框OA1~OA6。The
請同時參照圖5。圖5顯示本發明一實施例中,圖形處理電路230的方塊圖。圖形處理電路230包含複數圖形處理單元電路PD1~PD6。Please also refer to Figure 5. FIG. 5 shows a block diagram of the
資源配置軟體RGN在接收物件辨識資訊ODI後,可據以判斷各物件圖框OF1~OF6所需要進行的處理,並將物件圖框OF1~OF6對應的物件儲存區塊BB1~BB6的尺寸大小及位址告知圖形處理單元電路PD1~PD6,以使圖形處理單元電路PD1~PD6據以讀取物件圖框OF1~OF6進行處理。After receiving the object identification information ODI, the resource allocation software RGN can judge the processing required for each object frame OF1~OF6, and store the size and size of the object storage blocks BB1~BB6 corresponding to the object frame OF1~OF6. The address is notified to the graphics processing unit circuits PD1-PD6, so that the graphics processing unit circuits PD1-PD6 read the object frames OF1-OF6 for processing.
圖形處理電路230對物件圖框OF1~OF6進行的處理包含例如但不限於圖框的放大與縮小、圖形格式的轉換或其組合。The processing performed by the
於一實施例中,圖形處理電路230可依據包含縮放參數的圖形處理參數GS1~GS6處理物件圖框OF1~OF6。資源配置軟體RGN可藉由將圖形處理參數GS1~GS6以及物件儲存區塊BB1~BB6的位址等資訊寫入圖形處理單元電路PD1~PD6對應的暫存器(未繪示),以使圖形處理單元電路PD1~PD6讀取後據以運作。In one embodiment, the
於一實施例中,圖形處理單元電路PD1~PD6對物件圖框OF1~ OF6進行格式轉換以具有和原始影像OI相同之影像格式。舉例而言,原始影像OI之影像格式可為例如,但不限於ARGB8888或AYUV8888。圖形處理單元電路PD1~PD6可將物件圖框OF1~OF6的格式轉換以設置為上述兩種格式其中之一,以與原始影像OI之影像格式對應。In one embodiment, the graphics processing unit circuits PD1-PD6 perform format conversion on the object frames OF1-OF6 to have the same image format as the original image OI. For example, the image format of the original image OI may be, for example, but not limited to ARGB8888 or AYUV8888. The graphics processing unit circuits PD1~PD6 can convert the format of the object frames OF1~OF6 to be set to one of the above two formats, corresponding to the image format of the original image OI.
實作上,上述的圖形處理單元電路PD1~PD6可藉由例如,但不限於特定應用積體電路(application specific integrated circuit;ASIC)實現。In practice, the graphics processing unit circuits PD1 - PD6 mentioned above can be implemented by, for example, but not limited to, application specific integrated circuits (ASIC).
疊加電路240配置以將處理後物件圖框OA1~OA6疊加於原始影像OI上,進而輸出合成影像SI。於一實施例中,資源配置軟體RGN可根據物件辨識資訊ODI配置一組疊加參數SP1~SP6,進而使疊加電路240根據疊加參數SP1~SP6進行疊加。資源配置軟體RGN可藉由將疊加參數SP1~SP6的資訊寫入疊加電路240對應的暫存器(未繪示),以使疊加電路240讀取後據以運作。The superimposing
於一實施例中,疊加參數SP1~SP6包含圖形順序層級。 舉例而言,資源配置軟體RGN可根據物件辨識資訊ODI之遠近資訊設置圖形順序層級。當其中之一物件(例如物件OB1)在相對較近位置時,所對應的其中之一處理後物件圖框(例如處理後物件圖框OA1)具有較高的圖形順序層級。當其中之一物件(例如物件OB3)在相對較遠位置時,所對應的其中之一處理後物件圖框(例如處理後物件圖框OA3)具有較低的圖形順序層級。於一實施例中,原始影像OI被設置以具有最低的圖形順序層級。In one embodiment, the overlay parameters SP1 - SP6 include graphic order levels. For example, the resource configuration software RGN can set the graphics sequence level according to the distance information of the object identification information ODI. When one of the objects (such as the object OB1 ) is at a relatively close position, the corresponding one of the processed object frames (such as the processed object frame OA1 ) has a higher graphic sequence level. When one of the objects (such as the object OB3 ) is at a relatively far position, the corresponding one of the processed object frames (such as the processed object frame OA3 ) has a lower graphic sequence level. In one embodiment, the original image OI is set to have the lowest graphic order level.
於另一實施例中,疊加參數SP1~SP6包含透明度,且透明度可相應圖形順序層級設置。當其中之一物件在相對較近位置時,所對應的其中之一處理後物件圖框不僅具有較高的圖形順序層級,亦具有較低的透明度。當其中之一物件在相對較遠位置時,所對應的其中之一處理後物件圖框不僅具有較低的圖形順序層級,亦具有較高的透明度。In another embodiment, the superposition parameters SP1-SP6 include transparency, and the transparency can be set corresponding to the sequence level of the graphics. When one of the objects is at a relatively close position, the corresponding frame of one of the processed objects not only has a higher graphic sequence level, but also has a lower transparency. When one of the objects is at a relatively far position, the corresponding frame of one of the processed objects not only has a lower graphic sequence level, but also has a higher transparency.
於一實施例中,疊加電路240可藉由逐像素的方式來進行疊加。藉由資源配置軟體RGN設定的疊加位置,疊加電路240可對原始影像OI中的各目標像素判斷其是否對應到任一處理後物件圖框OA1~OA6的位置。若目標像素對應到任一處理後物件圖框OA1~OA6的範圍,疊加電路240將接收對應的處理後物件圖框OA1~OA6的像素資料,並與原始影像OI的目標像素疊加。若目標像素沒有對應到任一處理後物件圖框OA1~OA6的範圍,疊加電路240將直接輸出原始影像OI的目標像素。In one embodiment, the
於一實施例中,當目標像素對應到多個處理後物件圖框OA1~OA6的範圍時,疊加電路240可根據圖形順序層級來輸出其中一個處理後物件圖框OA1~OA6的像素資料(例如具有最高圖形順序層級者),並與原始影像OI的目標像素疊加。In one embodiment, when the target pixel corresponds to the range of multiple processed object frames OA1-OA6, the
請參照圖6。圖6顯示本發明另一實施例中,圖形處理電路230以及疊加電路240的方塊圖。類似圖5的圖形處理電路230,圖6的圖形處理電路230包含複數圖形處理單元電路PD1~PD6。然而於本實施例中,疊加電路240更包含複數疊加子電路SC1~SC6。Please refer to Figure 6. FIG. 6 shows a block diagram of a
疊加子電路SC1~SC6分別對應於圖形處理單元電路PD1~PD6其中之一,並自第一個疊加子電路SC1~SC6起依序分別根據疊加參數SP1~SP6將處理後物件圖框OA1~OA6其中之一疊加於原始影像OI上,並由最後一個疊加子電路SC6輸出合成影像SI。The superposition sub-circuits SC1~SC6 respectively correspond to one of the graphics processing unit circuits PD1~PD6, and sequentially convert the processed object frame OA1~OA6 according to the superposition parameters SP1~SP6 from the first superimposition subcircuit SC1~SC6. One of them is superimposed on the original image OI, and the final superimposition sub-circuit SC6 outputs the synthesized image SI.
於一實施例中,疊加子電路SC1~SC6可被設置以根據圖形順序層級的順序來將各物件圖框OA1~OA6進行疊加,而不必須如圖6所示的順序進行疊加。In an embodiment, the superimposing sub-circuits SC1 - SC6 can be configured to superimpose the respective object frames OA1 - OA6 according to the order of the graphic sequence level, instead of the order shown in FIG. 6 .
在部分技術中,儘管原始影像中的物件可被分別辨識,卻必須繪製單一且涵蓋所有物件的大圖框。當物件在原始影像中分布較為分散時,將使圖框包含過多非物件的影像內容,而造成記憶體使用上的浪費。並且,單一圖框的形式並無法針對個別物件進行不同的設定,在顯示上的運用彈性不足。In some techniques, although the objects in the original image can be identified separately, it is necessary to draw a single large frame covering all objects. When objects are scattered in the original image, the frame will contain too much non-object image content, resulting in waste of memory usage. Moreover, the form of a single frame cannot be set differently for individual objects, and the flexibility of display is insufficient.
本發明的影像物件疊加裝置可針對個別物件進行辨識並繪製物件圖框,不僅大幅降低記憶體的使用量,更可依需求而對物件圖框進行不同的設定,達到具有彈性的顯示效果。The image object superimposing device of the present invention can identify individual objects and draw object frames, which not only greatly reduces the usage of memory, but also allows different settings for object frames according to requirements to achieve flexible display effects.
須注意的是,在上述實施例中,物件、物件圖框以及處理後物件圖框的數目僅為一範例。實作上,物件、物件圖框以及處理後物件圖框的數目隨接收到的原始影像不同而有所不同。本發明並不限於此。It should be noted that, in the above embodiments, the numbers of objects, object frames and processed object frames are just an example. In practice, the numbers of objects, object frames and processed object frames vary with the received original images. The present invention is not limited thereto.
並且,在上述實施例中,物件辨識資訊、圖形設定參數以及疊加參數所包含的內容僅為一範例。實作上,物件辨識資訊、圖形設定參數以及疊加參數所包含的內容可依實際需求而有所不同。本發明並不限於此。Moreover, in the above-mentioned embodiments, the content contained in the object identification information, graphic setting parameters, and superposition parameters is just an example. In practice, the content contained in the object identification information, graphics setting parameters and overlay parameters may vary according to actual needs. The present invention is not limited thereto.
請參照圖7。圖7顯示本發明一實施例中,一種影像物件疊加方法700的流程圖。Please refer to Figure 7. FIG. 7 shows a flow chart of a
除前述裝置外,本發明另揭露一種影像物件疊加方法700,應用於例如,但不限於圖2的影像物件疊加裝置130中。影像物件疊加方法700之一實施例如圖7所示,包含下列步驟。In addition to the aforementioned devices, the present invention further discloses a
於步驟S710:由物件辨識電路210對原始影像OI包含的複數物件OB1~OB6進行辨識以產生物件辨識資訊ODI。In step S710 : the
於步驟S720:由圖形繪製電路220根據物件辨識資訊ODI繪製複數物件圖框OF1~OF6以儲存至記憶體120,其中物件圖框OF1~OF6分別對應物件OB1~OB6,且物件圖框OF1~OF6使用記憶體120的空間總和小於原始影像OI的資料大小。In step S720: the
於步驟S730:由圖形處理電路230包含的複數圖形處理單元電路PD1~PD6對物件圖框OF1~OF6進行處理以產生複數處理後物件圖框OA1~OA6。In step S730: the plurality of graphics processing unit circuits PD1-PD6 included in the
於步驟S740:由疊加電路240將處理後物件圖框OA1~OA6疊加於原始影像OI上,進而輸出合成影像SI。In step S740 : the
實作上,物件、物件圖框以及處理後物件圖框的數目隨接收到的原始影像不同而有所不同。並且,物件辨識資訊、圖形設定參數以及疊加參數所包含的內容可依實際需求而有所不同。本發明並不限於此。In practice, the numbers of objects, object frames and processed object frames vary with the received original images. Moreover, the content contained in the object identification information, graphic setting parameters and overlay parameters may vary according to actual needs. The present invention is not limited thereto.
需注意的是,上述的實施方式僅為一範例。於其他實施例中,本領域的通常知識者當可在不違背本發明的精神下進行更動。應瞭解到,在上述的實施方式中所提及的步驟,除特別敘明其順序者外,均可依實際需要調整其前後順序,甚至可同時或部分同時執行。It should be noted that the above-mentioned implementation is just an example. In other embodiments, those skilled in the art can make modifications without departing from the spirit of the present invention. It should be understood that, unless the order of the steps mentioned in the above embodiments is specifically stated, the order of the steps may be adjusted according to actual needs, and may even be executed simultaneously or partly simultaneously.
本發明中的影像處理系統及其影像物件疊加裝置及方法可針對個別物件進行辨識並繪製物件圖框,不僅大幅降低記憶體的使用量,更可依需求而對物件圖框進行不同的設定,達到具有彈性的顯示效果。The image processing system and its image object overlay device and method in the present invention can identify individual objects and draw object frames, which not only greatly reduces the amount of memory used, but also allows different settings for object frames according to requirements. A flexible display effect is achieved.
雖然本發明之實施例如上所述,然而該些實施例並非用來限定本發明,本技術領域具有通常知識者可依據本發明之明示或隱含之內容對本發明之技術特徵施以變化,凡此種種變化均可能屬於本發明所尋求之專利保護範疇,換言之,本發明之專利保護範圍須視本說明書之申請專利範圍所界定者為準。Although the embodiments of the present invention are as described above, these embodiments are not intended to limit the present invention, and those skilled in the art can make changes to the technical characteristics of the present invention according to the explicit or implicit contents of the present invention. All these changes may belong to the scope of patent protection sought by the present invention. In other words, the scope of patent protection of the present invention must be defined by the scope of patent application in this specification.
100:影像處理系統 110:影像擷取裝置 120:記憶體 130:影像物件疊加裝置 140:顯示裝置 200:處理器 210:物件辨識電路 230:圖形繪製電路 230:圖形處理電路 240:疊加電路 250:記憶體介面電路 700:影像物件疊加方法 S710~S740:步驟 BB1~BB6:物件儲存區塊 GS1~GS6:圖形處理參數 IB:原始影像儲存區塊 OA1~OA6:處理後物件圖框 OB1~OB6:物件 ODI:物件辨識資訊 OF1~OF6:物件圖框 OI:原始影像 PD1~PD6:圖形處理單元電路 RGN:資源配置軟體 SC1~SC6:疊加子電路 SI:合成影像 SP1~SP6:疊加參數 100: Image processing system 110: image capture device 120: memory 130:Image object overlay device 140: display device 200: Processor 210: Object identification circuit 230: Graphic drawing circuit 230: graphics processing circuit 240:Superposition circuit 250: memory interface circuit 700: Image object overlay method S710~S740: Steps BB1~BB6: object storage block GS1~GS6: Graphics processing parameters IB: Original image storage block OA1~OA6: object frame after processing OB1~OB6: Object ODI: Object Identification Information OF1~OF6: object frame OI: original image PD1~PD6: graphics processing unit circuit RGN: Resource Allocation Software SC1~SC6: superposition sub-circuit SI: Synthetic Image SP1~SP6: Overlay parameters
[圖1]顯示本發明之一實施例中,一種影像處理系統的方塊圖; [圖2]顯示本發明一實施例中,記憶體以及影像物件疊加裝置的方塊圖; [圖3]顯示本發明一實施例中,原始影像的示意圖; [圖4]顯示本發明一實施例中,物件圖框的示意圖; [圖5]顯示本發明一實施例中,圖形處理電路的方塊圖; [圖6]顯示本發明另一實施例中,圖形處理電路以及疊加電路的方塊圖;以及 [圖7]顯示本發明之一實施例中,一種影像物件疊加方法的流程圖。 [Fig. 1] shows a block diagram of an image processing system in one embodiment of the present invention; [Fig. 2] shows a block diagram of the memory and image object superimposition device in one embodiment of the present invention; [Fig. 3] shows a schematic diagram of an original image in an embodiment of the present invention; [Fig. 4] shows a schematic diagram of an object frame in an embodiment of the present invention; [Fig. 5] shows a block diagram of a graphics processing circuit in an embodiment of the present invention; [Fig. 6] shows a block diagram of a graphics processing circuit and an overlay circuit in another embodiment of the present invention; and [ FIG. 7 ] shows a flow chart of a method for overlaying image objects in an embodiment of the present invention.
120:記憶體 120: memory
130:影像物件疊加裝置 130:Image object overlay device
200:處理器 200: Processor
210:物件辨識電路 210: Object identification circuit
220:圖形繪製電路 220: Graphic drawing circuit
230:圖形處理電路 230: graphics processing circuit
240:疊加電路 240:Superposition circuit
250:記憶體介面電路 250: memory interface circuit
BB1~BB6:物件儲存區塊 BB1~BB6: object storage block
IB:原始影像儲存區塊 IB: Original image storage block
GS1~GS6:圖形處理參數 GS1~GS6: Graphics processing parameters
OA1~OA6:處理後物件圖框 OA1~OA6: object frame after processing
ODI:物件辨識資訊 ODI: Object Identification Information
OF1~OF6:物件圖框 OF1~OF6: object frame
OI:原始影像 OI: original image
PD1~PD6:圖形處理單元電路 PD1~PD6: graphics processing unit circuit
RGN:資源配置軟體 RGN: Resource Allocation Software
SI:合成影像 SI: Synthetic Image
SP1~SP6:疊加參數 SP1~SP6: Overlay parameters
Claims (15)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111128435A TWI811043B (en) | 2022-07-28 | 2022-07-28 | Image processing system and image object superimposition apparatus and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111128435A TWI811043B (en) | 2022-07-28 | 2022-07-28 | Image processing system and image object superimposition apparatus and method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI811043B true TWI811043B (en) | 2023-08-01 |
TW202405745A TW202405745A (en) | 2024-02-01 |
Family
ID=88585671
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111128435A TWI811043B (en) | 2022-07-28 | 2022-07-28 | Image processing system and image object superimposition apparatus and method thereof |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI811043B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI473038B (en) * | 2012-03-21 | 2015-02-11 | Ind Tech Res Inst | Image processing apparatus and image processing method |
CN102594857B (en) * | 2010-10-11 | 2015-11-25 | 微软技术许可有限责任公司 | Image recognition on mobile device is with shared |
TWI566601B (en) * | 2015-02-25 | 2017-01-11 | 光寶科技股份有限公司 | Image processing device and image depth processing method |
CN107945284B (en) * | 2017-12-11 | 2020-03-06 | 广州德科投资咨询有限公司 | Scene display method for automatic driving vehicle and intelligent glasses |
US10664722B1 (en) * | 2016-10-05 | 2020-05-26 | Digimarc Corporation | Image processing arrangements |
WO2020108082A1 (en) * | 2018-11-27 | 2020-06-04 | Oppo广东移动通信有限公司 | Video processing method and device, electronic equipment and computer readable medium |
-
2022
- 2022-07-28 TW TW111128435A patent/TWI811043B/en active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102594857B (en) * | 2010-10-11 | 2015-11-25 | 微软技术许可有限责任公司 | Image recognition on mobile device is with shared |
TWI473038B (en) * | 2012-03-21 | 2015-02-11 | Ind Tech Res Inst | Image processing apparatus and image processing method |
TWI566601B (en) * | 2015-02-25 | 2017-01-11 | 光寶科技股份有限公司 | Image processing device and image depth processing method |
US10664722B1 (en) * | 2016-10-05 | 2020-05-26 | Digimarc Corporation | Image processing arrangements |
CN107945284B (en) * | 2017-12-11 | 2020-03-06 | 广州德科投资咨询有限公司 | Scene display method for automatic driving vehicle and intelligent glasses |
WO2020108082A1 (en) * | 2018-11-27 | 2020-06-04 | Oppo广东移动通信有限公司 | Video processing method and device, electronic equipment and computer readable medium |
Also Published As
Publication number | Publication date |
---|---|
TW202405745A (en) | 2024-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11475238B2 (en) | Keypoint unwarping for machine vision applications | |
US10868985B2 (en) | Correcting pixel defects based on defect history in an image processing pipeline | |
WO2018214365A1 (en) | Image correction method, apparatus, device, and system, camera device, and display device | |
US9787922B2 (en) | Pixel defect preprocessing in an image signal processor | |
JP2009165106A (en) | Image distortion correction | |
US11024006B2 (en) | Tagging clipped pixels for pyramid processing in image signal processor | |
TW200903347A (en) | Edge mapping using panchromatic pixels | |
WO2021258579A1 (en) | Image splicing method and apparatus, computer device, and storage medium | |
US9317909B2 (en) | Image subsystem including image feature detection hardware component and image processing system including the same | |
CN108198189B (en) | Picture definition obtaining method and device, storage medium and electronic equipment | |
CN111028276A (en) | Image alignment method and device, storage medium and electronic equipment | |
CN111127358A (en) | Image processing method, device and storage medium | |
US20080170812A1 (en) | Image composition processing method, computer system with image composition processing function | |
TWI811043B (en) | Image processing system and image object superimposition apparatus and method thereof | |
US10375368B2 (en) | Image data conversion | |
CN108875733B (en) | Infrared small target rapid extraction system | |
US20080170805A1 (en) | Method and system for adding dynamic pictures to real-time image | |
CN113393391B (en) | Image enhancement method, image enhancement device, electronic apparatus, and storage medium | |
CN115240124A (en) | Image processing system, image object superposition device and method | |
CN111242087B (en) | Object identification method and device | |
TWI482099B (en) | Image processing and recording system and image processing and recording method thereof | |
CN110166710A (en) | Image composition method, device, equipment and medium | |
CN113824894A (en) | Exposure control method, device, equipment and storage medium | |
CN110705336B (en) | Image processing method, system, electronic device and readable storage medium | |
CN107633498B (en) | Image dark state enhancement method and device and electronic equipment |